npm - @openwop/openwop-conformance - Versions diffs - 1.33.0 → 1.34.0 - Mend

@openwop/openwop-conformance 1.33.0 → 1.34.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (8) hide show

package/README.md +2 -2
package/package.json +1 -1
package/src/scenarios/voice-bargein-no-partial-leak.test.ts +61 -0
package/src/scenarios/voice-interim-not-durable.test.ts +59 -0
package/src/scenarios/voice-streamref-tenant-bound.test.ts +59 -0
package/src/scenarios/voice-synthesis-streaming.test.ts +77 -0
package/src/scenarios/voice-transcription-streaming.test.ts +64 -0
package/src/scenarios/voice-transcription-unadvertised.test.ts +46 -0

package/README.md CHANGED Viewed

@@ -92,7 +92,7 @@ Exit code is non-zero on any failed assertion.
 ## What's Covered
-The current suite has 359 scenario files under `src/scenarios/`. 2026-06-23 (RFC 0107 — publishable declarative pack kinds) added one: `registry-declarative-kinds.test.ts` (always-on server-free — the registry version-manifest carries the `kind` discriminator + per-kind declarative payload, `runtime` is conditional on `kind` via `allOf if/then/else`, published artifact-type and connection manifests validate, and a declarative-with-`runtime` or node-without-`runtime` manifest is rejected). 2026-06-23 (RFC 0106 — real-time voice session profile, Phase 2) added one: `voice-event-payloads-shape.test.ts` (always-on server-free — all seven `voice.*` types are in the `RunEventType` enum, each has a payload `$def` via `typeIndex`, `voice.transcript` REQUIRES `contentTrust:"untrusted"` (the schema-enforced half of `voice-transcript-untrusted`), `voice.synthesis_chunk` is metadata-shaped (seq+mimeType required; bytes by `url`/`streamRef`), and the content-free events reject unknown properties). Phase 2 also lands the `voice.*` payload `$defs` in `run-event-payloads.schema.json` + the `asyncapi.yaml` messages + the four §F `SECURITY/invariants.yaml` rows (1 protocol-tier `voice-transcript-untrusted` + 3 reference-impl behavioral, graduating at `Active → Accepted`). The gated behavioral legs (`voice-transcription-streaming`/`-unadvertised`, `voice-synthesis-streaming` + the three behavioral invariant scenarios) land with the reference host at `Active → Accepted`. 2026-06-23 (RFC 0106 — real-time voice session profile, Phase 1) added one: `aiproviders-realtimevoice-shape.test.ts` (always-on server-free — the `aiProviders.realtimeVoice` object advertisement: the four sub-flags `transcription`/`synthesis`/`turnDetection`/`bargeIn` are declared, `realtimeVoice` is absent from `aiProviders.required`, the `turnDetection`/`bargeIn ⇒ transcription` `dependentRequired` closure and the `synthesis ⇒ speechSynthesis` if/then closure hold via Ajv2020, and out-of-enum / boolean sub-flag values are rejected). The gated behavioral legs (`voice-transcription-streaming` / `-unadvertised`, `voice-synthesis-streaming`) and the four §F live-ingress invariant scenarios land in Phase 2 at the `Active → Accepted` cycle. 2026-06-22 (RFC 0101 — multi-party group conversation) added two — `multi-party-conversation-shape.test.ts` (always-on server-free — asserts the three additive RFC 0101 wire facts: a 3-agent council `conversation.opened` participant roster (instance ids) + a user opening turn validates, every `role: 'agent'` turn carrying a roster-instance `speakerId` validates while one OMITTING `speakerId` MUST FAIL schema validation (the `allOf`/`if role==='agent' then required:['speakerId']` conditional), a non-AgentRef participant item is rejected, the `capabilities.multiPartyConversation { supported, maxParticipants? }` block is declared + closed and rejects extras / `maxParticipants:1` / a missing `supported`, and the non-participant membership predicate is asserted server-free) and `multi-party-conversation-behavioral.test.ts` (capability-gated on `multiPartyConversation.supported` via `behaviorGate('openwop-multi-party-conversation', …)` — drives the conformance-only seam `POST /v1/host/sample/conversation/multi-party/{open,exchange}` (`host-sample-test-seams.md`, since RFC 0101 mints no normative client trigger to open a council): a 3-agent council opens and a roster-valid attributed agent turn is accepted, while a `role:'agent'` turn missing `speakerId`, a non-participant `speakerId`, and an over-`maxParticipants` open are each rejected with `error.code:'validation_error'` (status-tolerant 400/422 per RFC 0005 §E); soft-skips on 404/405 — reference impl: the postgres example host). 2026-06-20 (RFC 0105 — speech synthesis adapter) added three: `aiproviders-speechsynth-shape.test.ts` (always-on server-free — the `aiProviders.speechSynthesis` `const "supported"` flag is declared, absent from `aiProviders.required`, and a string-const advertisement validates while the object form `{supported:true}` is rejected), `speech-synthesis-roundtrip.test.ts` (gated on `aiProviders.speechSynthesis === "supported"` via `behaviorGate('openwop-speech-synthesis', …)` — an advertising host's `callSpeechSynthesizer` round-trip via the `POST /v1/host/sample/ai/call-speech-synthesizer` seam returns `audio` with EXACTLY ONE of `url`/`base64`, a non-empty `mimeType`, and the echoed `voiceId`; soft-skips on 404), and `speech-synthesis-unadvertised.test.ts` (gated-by-absence via `behaviorGate('openwop-speech-synthesis-unadvertised', …)` — a host NOT advertising `speechSynthesis` MUST reject the call with `speech_synthesis_unsupported`, never a silent no-op). 2026-06-19 (RFC 0104 — portable HITL approver routing) added one: `interrupt-approver-routing.test.ts` (server-free Ajv2020 — the `interrupt.approverRouting` capability block shape, the additive optionality of `approverGroupRefs` / `approverRoleRefs` / `audience` on the `ApprovalData` schema, the closed `audience` object, and the §"Portable approver routing" `notifyTargets` reference rule that `audience` DEFAULTS to the resolved eligibility union when omitted and OVERRIDES it when present; the capability-gated leg asserts an advertising host's `interrupt.approverRouting` is honest — `refKinds` ⊆ {group, role}, `audience` boolean — and soft-skips when the host does not advertise the capability). 2026-06-17 (RFC 0103 — localized content surface) added one: `localized-content-delivery.test.ts` (server-free Ajv2020 — the four content schemas + the §C `resolveSection` merge + §A capability coherence; the public test for `content-published-cache-no-draft` / `content-response-tenant-scoped` / `content-no-cross-tenant-enumeration`; the live legs gate on `capabilities.content.supported` and soft-skip without a `GET /v1/content/pages/{slug}` target). 2026-06-15 (RFC 0102 — A2UI agent-authored interface surfaces) added five: `a2ui-surface-shape.test.ts` (server-free Ajv2020 — the closed core `ui.a2ui-surface` payload validates, while an out-of-catalog component / extra script-bearing property / unenumerated `catalogVersion` / `action.target` outside `enum["resume","exchange"]` each fail; the structural half of `a2ui-action-confinement` and the enabling precondition for the render-side `a2ui-surface-no-code-exec` / `a2ui-surface-no-network-egress` reference-app probes), `a2ui-surface-degrades.test.ts` (the kind is optional/advertised, not a MUST-recognize universal kind, and an unadvertised kind is gated — N6 — never crashing the run), `a2ui-surface-version-refusal.test.ts` (the enumerated `catalogVersion` rejects an unadvertised version → `unknown_schema_version`, and the surface schema carries no external `$ref`), `a2ui-surface-replay.test.ts` (all `$ref`s internal so a stored surface `:fork`/replays deterministically; same-`correlationId` + divergent `type` → `envelope_correlation_conflict`), and `a2ui-untrusted-blocks-approval.test.ts` (a `meta.contentTrust:'untrusted'` surface is trust-gated and MUST NOT advance an approval interrupt — composition of `untrusted_content_blocks_approval`). The four behavioral legs soft-skip on 404 (host-pending; the `openwop-app` reference renderer is the render-side probe). 2026-06-14 (RFCs 0099/0100 — external-event trigger ingestion + async/durable A2A tasks) added one new scenario (`trigger-ingestion.test.ts`) and extended `a2a-task-roundtrip.test.ts` with the RFC 0100 async subtests: `trigger-ingestion.test.ts` (RFC 0099 — always-on `TriggerEvent` / `TriggerSubscriptionRegistration` schema legs incl. the §F.1 per-source one-of, the `AttachmentRef.ref`-only rule + raw-URL rejection backing `trigger-ingestion-ssrf`, and the content-free `trigger.delivery.attempted` shape backing `trigger-ingestion-content-redaction`; plus a capability-gated behavioral leg on `triggerBridge.ingestion` driving the `POST /v1/host/sample/trigger-bridge/ingest` seam for SSRF refusal + header-redaction), and the `a2a-task-roundtrip.test.ts` additions (RFC 0100 — always-on `A2ATaskState` + `capabilities.a2a` shape legs incl. the lowercase-hyphen state enum, the `PushConfig` `url`-required + truncated-`tokenFingerprint` rule backing `a2a-push-egress-ssrf`, the no-inline-inputs `additionalProperties:false` SR-1 check; plus capability-gated durable-`tasks/get`-after-disconnect and push-SSRF behavioral legs on `a2a.durableTasks` / `a2a.pushNotifications` via the `/v1/host/sample/a2a/tasks/*` seam). 2026-06-13 (RFCs 0096/0097/0098 — reviewable learning, standing goals, agent-platform portability) added three always-on-plus-gated scenarios: `proposal-reviewable-learning.test.ts` (RFC 0096 — the `agents.proposals` shape + the `Proposal` round-trip incl. the dropped `rule` kind + the content-free `proposal.{created,activated}` events, plus a gated apply-without-scope→403 leg; backs `proposal-inert-until-applied` + `proposal-no-resynthesis`), `goal-standing-continuation.test.ts` (RFC 0097 — the `agents.goals` shape + the `Goal` round-trip + the content-free `goal.{evaluated,closed}` events, plus gated bounded-termination→422 + judge-only-completion legs; backs `goal-continuation-bounded` + `goal-completion-judge-only`), and `export-bundle-portability.test.ts` (RFC 0098 — the `portability` shape incl. the `import⇒dryRun` if/then + the `ExportBundle` round-trip rejecting every credential-named field + the content-free `import.applied` event, plus a gated literal-credential-import→422 leg; backs `export-bundle-no-credential-material`). 2026-06-11 (RFCs 0093/0094 — protocol hardening + wire-shape reconciliation) added five: `version-fold.test.ts` (the `version-negotiation.md` §`X-Force-Engine-Version` cross-version matrix through the previously-orphaned `conformance-version-fold` fixture — closes catalog gap F5; soft-skips when `Capabilities.testing.forceEngineVersionRange` is unadvertised), `stream-text-fixture.test.ts` (the `stream-modes.md` §`messages` fold through the deterministic `stream-text` mock provider + the previously-orphaned `conformance-stream-text` fixture — closes catalog gap F1), `i18n-negotiation.test.ts` (gated on `capabilities.i18n` via `behaviorGate('openwop-i18n', …)` — an unsupported or malformed `Accept-Language` never 400s, `Content-Language` reflects the locale actually used, and error `code` strings stay the canonical English tokens), `grpc-transport.test.ts` (gated on `capabilities.grpc` via `behaviorGate('openwop-grpc-transport', …)` — advertisement-shape only per `grpc-transport.md` §Field semantics: `service` MUST be `openwop.v1.Engine`, the `tls` enum, `grpcs?://` endpoint URIs, `supportedTransports` includes `grpc` when exposed, production claimants require `tls: "required"`; no gRPC dialing), and `webhook-tenant-isolation.test.ts` (RFC 0093 §A.3 — backs the new protocol-tier `webhook-cross-tenant-isolation` invariant; a two-tenant proof through the `/v1/host/sample/test/surface` seam plus black-box registration-surface scoping). `spec-corpus-validity.test.ts` also gained the RFC 0094 §A satisfiability probe: canonical `createRun` bodies MUST pass the composed request schema (closed via `unevaluatedProperties: false` at the composition site, never inside an `allOf` branch) and an undeclared property MUST fail. 2026-06-07 (RFCs 0090/0091/0092 — verifier turn + convergence, multimodal perception input, agent capability requirements) added six: the always-on, server-free shape probes `agent-verifier-shape.test.ts`, `aiproviders-input-shape.test.ts`, `agent-requires-capabilities-shape.test.ts`, plus the capability-gated **behavioral** legs `agent-capability-degraded-projection.test.ts` (RFC 0092 §B — the `degraded[]` projection on `GET /v1/agents`, black-box, non-vacuous via `OPENWOP_DEGRADED_CAPABILITY_AGENT_ID`), `callai-multimodal.test.ts` (RFC 0091 §A/§B — advertised modality accepted / unadvertised → `unsupported_modality`, via the `POST /v1/host/sample/ai/call` seam), and `verifier-gating.test.ts` (RFC 0090 §B — a `fail` verdict blocks commit, via the `POST /v1/host/sample/agents/verify-run` seam). The three behavioral legs soft-skip by default and hard-fail under `OPENWOP_REQUIRE_BEHAVIOR=true` — the Active→Accepted reference-host proof for each RFC. 2026-06-02 (RFC 0082 §B — deployment channel resolve-and-pin, production-path coverage) added `agent-channel-dispatch.test.ts` (capability-gated on `agents.deployment.supported` + the seeded `conformance-agent-channel-dispatch` fixture + advertised `replay` mode via `behaviorGate('openwop-deployment-channel-dispatch', …)` — proves the §B pin from a REAL run graph, complementing `agent-deployment-lifecycle.test.ts` Leg 4's host-sample seam: a canonical `POST /v1/runs` of a node binding `agent.channel:"stable"` MUST record `resolvedChannel` + `resolvedAgentVersion` on `agent.invocation.started` (RFC 0077), a `:fork{mode:"replay"}` MUST re-read that recorded version, and the seam-guarded Leg 3 MOVES the channel then asserts a replay STILL carries the original pin — never re-resolving a moved channel; soft-skips by default, hard-fails under `OPENWOP_REQUIRE_BEHAVIOR=true` — the production-path proof of the §B contract). 2026-06-01 (RFC 0085 — `openwop-agent-platform` meta-profile, the Active→Accepted behavioral gate) added `agent-platform-aggregate-evidence.test.ts` (capability-gated on a host CLAIMING `openwop-agent-platform` in its live discovery `profiles[]` via `behaviorGate('openwop-agent-platform', …)` — the §C/§D honest-advertisement rule on the live `/.well-known/openwop`: the claim MUST satisfy the §B floor predicate (`isAgentPlatformPartial` → `partial`/`full`, never `none`), backed by the per-capability evidence not the profile string; `OPENWOP_AGENT_PLATFORM_TIER=full` forces the non-vacuous full bar — all governance terms + tenant installScope + all 16 §D terms; server-requiring, the always-on §B/§D derivation legs stay in `agent-platform-profile.test.ts` — the RFC 0085 → Accepted bar). 2026-06-01 (RFC 0084 — budget, quota + cost policy, the Active→Accepted behavioral gate) added `budget-enforcement.test.ts` (capability-gated on `budget.supported` via `behaviorGate('openwop-budget-enforcement', …)` — the §C/§D enforcement via the new `POST /v1/host/sample/budget/run` seam + the test event-log seam: a `hard-cost-exhaust` run emits the strict-ordered `budget.reserved → budget.consumed → budget.threshold.crossed{percent} → budget.exhausted → cap.breached{kind:"budget-cost"} → run.failed{error:"budget_exhausted"}` chain; a `model-denied` run is refused `budget_model_denied` BEFORE the provider call (fail-closed); an `advisory` host emits the `budget.*` events without stopping; every `budget.*` payload content-free backing `budget-no-pricing-leak`; new lib helper `src/lib/budgetPolicy.ts`; soft-skips on 404 — the RFC 0084 → Accepted bar). 2026-06-01 (RFC 0080 — agent memory capability reconciliation, the Active→Accepted behavioral gate) added `memory-degraded-projection.test.ts` (capability-gated on `agents.manifestRuntime.supported` + `memory.supported` via `behaviorGate('openwop-memory-degraded', …)` — the §C degraded-projection iff-contract on the NORMATIVE `GET /v1/agents`: a degraded inventory entry MUST carry `memoryDegraded:true` + a non-empty, unique `degradedMemoryDimensions[]` from the closed §A-name enum, a non-degraded entry MUST NOT, the inventory is non-empty, and the degraded branch runs non-vacuously when `OPENWOP_DEGRADED_AGENT_ID` names a known-degraded agent; black-box, no POST seam — the RFC 0080 → Accepted bar). This batch also documents the two RFC 0068 conformance seams (`POST /v1/host/sample/memory/consolidate` + `.../commitment/fire`) in `host-sample-test-seams.md` (the 0068 gated scenarios shipped in 1.14.0). 2026-06-01 (RFC 0034 — collector-side BYOK-canary inspection) added `otel-collector-canary-inspection.test.ts` (always-on server-free: stands up a real `OtelCollector`, POSTs synthetic OTLP/HTTP-JSON traces + metrics through its actual ingest path, and proves the new `findCanaryLeakage()` inspector catches a canary embedded in a span attribute / resource attribute / span name / metric data-point attribute while reporting ZERO hits on a redacted payload and never matching an empty canary — the non-vacuous proof that the conformance collector now inspects what the host's OTLP exporter ACTUALLY shipped over the wire, closing the `secret-leakage-otel-attribute` / `-debug-bundle-otel` collector-seam gap; the live capability-gated complement is the new collector-export describe block in `secret-leakage-otel-attribute.test.ts`). 2026-06-01 (RFC 0035 — sandbox wall-clock timeout, the 7th-of-8 graduation) added `sandbox-wasm-timeout.test.ts` (worker-driven server-free: `probeTimeout` in `wasm-sandbox-probe.ts` spawns a worker thread running the committed `misbehaving-timeout.wasm` + a main-thread kill-timer — the thread preemption a same-thread probe can't do — asserting `sandbox_timeout` with a well-behaved positive control; graduates `node-pack-sandbox-timeout` reference-impl→protocol, so 7 of 8 `node-pack-sandbox-*` invariants are now protocol-tier, only the JS-specific `no-eval` permanently exempt). 2026-05-31 (audit-response black-box / graduation batch) added three more: `sandbox-wasm-isolation.test.ts` (RFC 0035 — drives the committed `fixtures/wasm-sandbox/*.wasm` through `wasm-sandbox-probe.ts`: escape/capability-gate via static `WebAssembly.Module.imports()`, an OOB-store memory trap, double-instantiate isolation; 10/10; graduates 6 `node-pack-sandbox-*` invariants reference-impl→protocol), `workspace-cross-tenant-isolation-blackbox.test.ts` (RFC 0059 — two-credential black-box on the normative §C `/v1/host/workspace/files` endpoints: owner A writes, a second-tenant credential fails closed; no seam), and `prompt-resolution-chain-event.test.ts` (RFC 0029 — reads the durable `agent.promptResolved.chain[]` precedence record via the normative `GET /v1/runs/{runId}/events/poll`; no seam) — each the production-path proof that graduates its surface into the `openwop-core-standard` floor. 2026-05-31 (RFC 0088 — the `openwop-core-standard` Core Standard Profile, the audit-response Core Candidate target) added `core-standard-profile.test.ts` (always-on server-free derivation probe: `isCoreStandard` derives the §B floor — `openwop-core` ∧ `openwop-interrupts` ∧ (`openwop-stream-sse` ∨ `openwop-stream-poll`) — a bare `openwop-core` host without interrupts is excluded, a host with no event transport fails, and the annex is absent from `deriveProfiles` because it composes rather than redefines). 2026-05-31 (RFC 0082 — agent deployment lifecycle, the Active→Accepted behavioral gate) added `agent-deployment-lifecycle.test.ts` (capability-gated on `agents.deployment.supported` via `behaviorGate('openwop-deployment-lifecycle', …)` — the §E promotion contract via the new `POST /v1/host/sample/agents/deployment-transition` seam + the test event-log seam across four legs: `promote` (authorize RFC 0049 → approvalGate RFC 0051 → eval-verify RFC 0081 → content-free `deployment.promoted` with a seven-state `toState` + `toVersion`, the record validating `agent-deployment.schema.json`), `unauthorized` (fail-closed — `allowed:false`, no `deployment.promoted`, the behavioral leg of `deployment-promotion-fail-closed`), `eval-gate-unmet` (`eval_gate_unmet` denial, §E-3), and `channel-pin` (the §B `resolvedAgentVersion` recorded-fact on `agent.invocation.started`); new lib helper `src/lib/agentDeployment.ts`; soft-skips on 404 — the RFC 0082 → Accepted bar). 2026-05-31 (RFC 0081 — agent evaluation, the Active→Accepted behavioral gate) added `agent-eval-run.test.ts` (capability-gated on `agents.evalSuite.supported` via `behaviorGate('openwop-eval-run', …)` — the §B `mode:"eval"` projection via the new `POST /v1/host/sample/agents/eval-run` seam + the test event-log seam: `eval.started`-first → one `eval.scored` per task → `eval.completed`-once ordering (count == `eval.completed.taskCount`), the content-free `eval.scored` legs (`score` ∈ 0..1) backing `eval-summary-no-content-leak`, and the NORMATIVE `GET /v1/runs/{runId}/eval-summary` schema-valid `EvalSummary` round-trip with `passedCount <= taskCount`; new lib helper `src/lib/agentEval.ts`; soft-skips on 404 — the RFC 0081 → Accepted bar). 2026-05-31 (RFC 0083 — durable trigger bridge, the Active→Accepted behavioral gate) added `trigger-bridge-delivery.test.ts` (profile-gated on `openwop-trigger-bridge` derived from the live discovery doc — the §C delivery model via the `POST /v1/host/sample/trigger-bridge/deliver` seam + the test event-log seam: dedup→effectively-once `trigger.delivery.attempted{delivered}` (§C-1), retry-exhaustion→`{dead-lettered}` + `trigger.subscription.state.changed{toState:dead-lettered}` (§C-2 + RFC 0053), and the delivered run's `run.started.causationId` == the delivery id (§C / RFC 0040); both `trigger.*` events content-free; the always-on shape stays in `trigger-bridge-shape.test.ts`; new lib helper `src/lib/triggerBridge.ts`). 2026-05-31 (RFC 0087 — agent org-chart, the Active→Accepted behavioral gate) added two capability-gated behavioral scenarios (both gated on `agents.orgChart.supported`, black-box on the normative `/v1/agents/org-chart` surface — no new POST seam): `agent-org-chart-scoping.test.ts` (the `GET /v1/agents/org-chart` tree-shape — departments form an acyclic `parentDepartmentId` tree, members reference `host:<id>` roster entries — + the §D responsibility roll-up via `GET /v1/agents/org-chart/{departmentId}` with a deduped `responsibilities[]` union + the RFC 0074 cross-tenant 404 via `OPENWOP_CROSS_TENANT_ORG_CHART_DEPARTMENT_ID`) and `org-position-no-authority-escalation.test.ts` (the behavioral leg of the protocol-tier invariant — the live org-chart wire carries NO authority-bearing field on any member/department/responsibility-view object; the structural leg stays always-on in `agent-org-chart-shape.test.ts`, and the deeper RFC 0049/0051 authority-invariance legs stay reference-impl tier per the `agent-manifest-runtime` no-host-hook precedent). 2026-05-31 (RFCs 0086 + 0077 — the Active→Accepted behavioral gate) added four capability-gated behavioral scenarios so a non-steward host can be mechanically certified non-vacuously under `OPENWOP_REQUIRE_BEHAVIOR=true`: `agent-roster-attribution.test.ts` (RFC 0086 §B/§C; gated on `agents.roster.supported` — the normative `GET /v1/agents/roster` read shape + `total==roster.length`, the §C `roster.run.initiated`-before-`agent.invocation.started` ordering, the content-free payload backing `roster-attribution-no-content`, the durable work-item `triggerSubscriptionId`, and the RFC 0074 cross-tenant 404 via `OPENWOP_CROSS_TENANT_ROSTER_ID`), `agent-live-invocation-bracket.test.ts` (RFC 0077 §E; gated on `agents.liveRuntime.supported` — `agent.invocation.started`-first / `agent.invocation.completed`-last bracket, matching `invocationId`, `source`/`outcome` closed enums, content-free), `agent-live-structured-output.test.ts` (RFC 0077 §B step 6; gated on `agents.liveRuntime.structuredOutput` — a result violating `handoff.returnSchemaRef` fails the invocation `outcome:"failed"` rather than shipping as completed), and `agent-live-allowlist-enforced.test.ts` (RFC 0077 §F-1 / RFC 0002 §A14; gated on `agents.liveRuntime.supported` — a tool outside `toolAllowlist` is not callable); all four drive the documented `POST /v1/host/sample/roster/fire` + `POST /v1/host/sample/agents/live-invoke` seams plus the test event-log seam and soft-skip on 404 (these are the RFC 0086 / 0077 Active→Accepted bars). 2026-05-30 (RFC 0087 — agent org-chart, Draft -> Active) added `agent-org-chart-shape.test.ts` (always-on server-free: the `capabilities.agents.orgChart` shape + the `AgentOrgChart` round-trip + the non-`host:` member negative + the **§B structural non-authority guarantee** — the schema rejects a `scopes`/`canDispatch`/`permissions`/`authority` field on a member (`additionalProperties:false`), and a member's key set is exactly `{rosterId, departmentId, roleId, reportsTo}` — backing the protocol-tier `org-position-no-authority-escalation` invariant; no new RunEventType). 2026-05-30 (RFC 0086 — standing agent roster, Draft -> Active) added `agent-roster-shape.test.ts` (always-on server-free: the `capabilities.agents.roster` shape + the `AgentRosterEntry` round-trip + the `host:` `rosterId` + `agentRef` version-XOR-channel negatives + the content-free `roster.run.initiated` negatives backing the protocol-tier `roster-attribution-no-content` invariant + the additive `roster` inventory projection + RunEventType-enum membership). 2026-05-30 (RFC 0082 — agent deployment lifecycle, Draft -> Active) added `agent-deployment-shape.test.ts` (always-on server-free: the `capabilities.agents.deployment` shape + the `AgentDeployment` record round-trip + the `AgentRef` `channel` XOR `version` `not`-clause + the four `deployment.*` payloads + the content-free negatives backing the protocol-tier `deployment-event-no-content-leak` invariant). 2026-05-30 (RFC 0085 — `openwop-agent-platform` meta-profile, Draft -> Active) added `agent-platform-profile.test.ts` (always-on server-free derivation of the operational-annex `none`/`partial`/`full` status: all-floor ⇒ partial, missing-flag ⇒ none, the replay-OR-`nondeterminismPolicy.declared` term, floor+governance ⇒ full, missing-tenant-scope ⇒ partial-not-full per the honest-advertisement rule, eval/deploy/budget-are-advisory-not-hard-terms, + the `capabilities.nondeterminismPolicy.declared` shape). 2026-05-30 (RFC 0084 — budget, quota + cost policy, Draft -> Active) added `budget-policy-shape.test.ts` (always-on server-free: `budget-policy.schema.json` round-trip + the §A orthogonality guard — a wall-time field is rejected (it's RFC 0058's `runTimeoutMs`) — + threshold/onExhaustion negatives + the four content-free `budget.{reserved,consumed,threshold.crossed,exhausted}` payloads + the four `cap.breached{budget-*}` kinds + RunEventType-enum membership + the no-pricing-property structural check backing the protocol-tier `budget-no-pricing-leak` invariant + the `capabilities.budget`/`limits.maxBudget*` shape). 2026-05-30 (RFC 0083 — durable trigger + channel bridge, Draft -> Active) added `trigger-bridge-shape.test.ts` (always-on server-free: `trigger-subscription.schema.json` round-trip + missing-`state`/out-of-enum-`source`/unknown-property negatives + the four-state vocab + the two content-free `trigger.{subscription.state.changed,delivery.attempted}` payloads incl. closed `state`/`outcome` enums + RunEventType-enum membership + the `triggerBridge`/`webhooks.durable` capability shape + the `openwop-trigger-bridge` profile derivation incl. the no-dead-letter-sink negative). 2026-05-30 (RFC 0079 — credential provenance + egress policy, Draft -> Active) added `egress-provenance-shape.test.ts` (always-on server-free: `credential-provenance.schema.json` round-trip + `audiences:[]`/missing-`credentialId`/unknown-property negatives + the no-secret-property structural check backing the protocol-tier `egress-decision-no-secret-leak` invariant + the content-free `egress.decided` record incl. the `decision` enum + RunEventType-enum membership + the `httpClient.egressPolicy` shape; the behavioral `egress-credential-audience-bound` confused-deputy MUST is reference-impl tier, deferred to a host). 2026-05-30 (RFC 0078 — portable tool catalog, Draft -> Active) added `tool-descriptor-shape.test.ts` (always-on server-free: `tool-descriptor.schema.json` round-trip + the §C-1 `exec` ⇒ `host-extension` cross-field MUST (RFC 0069) + the `safetyTier`-required negative + `additionalProperties:false`, the `capabilities.toolCatalog` `supported`/`sources`/`sessionLifecycle` shape, and the two content-free `tool.session.{opened,closed}` payload $defs incl. the closed `outcome` enum + RunEventType-enum membership). 2026-05-30 (RFC 0080 — agent memory capability reconciliation, Draft -> Active) added `memory-capability-model-shape.test.ts` (always-on server-free: the additive `capabilities.memory.{writable,search,retention}` dimension shapes + malformed-instance negatives — `retention.ttl` non-boolean, out-of-enum `search.modes`, unknown property under `additionalProperties:false` — the `agent-inventory-response` `memoryDegraded`/`degradedMemoryDimensions` closed-enum fields, and the `openwop-memory` derivation surfacing for read/write + long-term hosts while withholding from `writable:false`). 2026-05-30 (RFC 0081 — agent evaluation, Draft -> Active) added `agent-eval-suite-shape.test.ts` (always-on server-free: the `capabilities.agents.evalSuite` shape + the `AgentEvalSuite`/`EvalSummary` schema round-trips + the three `eval.{started,scored,completed}` payloads + the content-free negatives — a task entry with a `taskOutput` body, a `safetyFinding` with an `excerpt` — backing the new `eval-summary-no-content-leak` SECURITY invariant). 2026-05-29 (RFC 0076 §B — `ctx.http.safeFetch` live-run audit) added `safefetch-live-audit.test.ts` (`behaviorGate('openwop-safefetch-live-audit', …)`, gated on `httpClient.safeFetch` + `toolHooks.prePostEvents`) — asserts the audit-when-both MUST against the **durable run event log** via the new `POST /v1/host/sample/http/safe-fetch-run` open seam + the test event-log seam, closing the seam-vs-production gap (a production `createSafeFetch()` with no audit hooks passes the inline `safefetch-behavior.test.ts` but FAILS this under `OPENWOP_REQUIRE_BEHAVIOR=true`); this is the RFC 0076 §B → Accepted bar; run seam soft-skips on 404 (host-pending). 2026-05-29 (RFC 0066 — `x-openwop-form` picker UX hints, Draft → Active) added `x-openwop-form-pack-manifest.test.ts` (always-on server-free: an annotated `configSchema` stays a valid 2020-12 schema + the advisory hints don't change what it accepts, each §A annotation matches the shape, an unknown `kind` validates for forward-compat, 3 negatives — missing/non-string `kind`, non-string `dependsOn`). 2026-05-29 (RFC 0076 §B — `ctx.http.safeFetch`) added `safefetch-behavior.test.ts` (seam-gated: SSRF block / DNS-rebinding / `Connection: upgrade` refusal / tool-hooks audit-when-both, via `POST /v1/host/sample/http/safe-fetch`; advertisement contract stays in `http-client-ssrf.test.ts`). 2026-05-29 (RFC 0076 §A — pack `runtime.requires[]` install gate) added two: `runtime-requires-shape.test.ts` (server-free closed-vocabulary validation — the 8 tokens validate, a raw builtin name is rejected, empty-array≡omission, `uniqueItems`) + `runtime-requires-install-gate.test.ts` (seam-gated install-grant / install-refuse → `pack_runtime_requirement_unmet` / non-sandbox SHOULD-projection, soft-skip on 404 via `POST /v1/host/sample/packs/install-gate`). 2026-05-29 (RFC 0047 — `host.oauth` authorization-code roundtrip) added `oauth-authorization-code-roundtrip.test.ts` — capability-gated on `capabilities.oauth.supported` + `grants` including `authorization_code`; drives the `POST /v1/host/sample/oauth/authorize-code-roundtrip` seam against the one canonical synthetic provider in `fixtures/oauth-providers/synthetic.json` (soft-skip on 404, Tier-2 host-pending), asserting a successful grant returns a credential REFERENCE (token persisted as a `host.credentials` entry) and that the authorization code / state / PKCE verifier / acquired access+refresh tokens never appear on any run-visible surface (RFC 0047 §C + §C.2 / `credential-payload-redaction`). Closes the RFC 0047 Tier-2 gap (capability-shape + redaction scenarios existed; the actual authorization-code dance was unexercised). 2026-05-26 (RFC 0070 — agent-manifest runtime) added `agent-manifest-runtime.test.ts`; 2026-05-26 (RFC 0071 — artifact-type + chat card packs) added six: `artifact-type-pack-manifest-validation.test.ts` + `artifact-schema-compile-bounded.test.ts` (server-free) + `artifact-type-pack-install.test.ts` + `artifact-type-store-without-render.test.ts` + `chat-card-pack-manifest-validation.test.ts` (server-free) + `chat-card-pack-execution.test.ts` (capability-gated, host-pending). 2026-05-26 (RFCs 0067 / 0068 / 0069 — spec-gap Draft cohort) added five scenarios: `byok-auth-modes.test.ts` (RFC 0067; always-on schema-shape of `aiProviders.authModes` + a discovery-gated §B auth-mode-contract cross-field check), `memory-consolidation-shape.test.ts` (RFC 0068; always-on shape of `agents.memoryConsolidation`/`agents.commitments` + the `agent.memory.consolidated`/`commitment.fired` payload $defs), `memory-consolidation-idempotent.test.ts` + `commitment-fired.test.ts` (RFC 0068; capability-gated behavioral, soft-skip on the documented `/v1/host/sample/memory/consolidate` + `/commitment/fire` seams), and `exec-not-protocol-tier.test.ts` (RFC 0069; always-on server-free structural assertion that the protocol corpus defines no `core.*`/`openwop.*` exec-class primitive — backs the `exec-must-not-be-protocol-tier` SECURITY invariant). 2026-05-25 (RFC 0061 — stateful agent-loop lifecycle, executionModel.version 5) added four `agent-loop-*.test.ts` scenarios: `-version5-shape` (always-on; validates `executionModel.statefulResume`/`transcriptWindow` + the 1–5 version ceiling) plus `-iteration-monotonic` (gated on `version >= 5`; `runOrchestrator.decided.iteration` increments 1,2,3… exactly once per turn), `-workspace-snapshot` (gated additionally on `host.workspace.supported`; a turn-i workspace write is invisible to turn i, visible to turn i+1), and `-stateful-resume` (gated on `statefulResume`; a mid-loop suspend resumes at the same iteration without resetting the counter) — the three behavioral scenarios drive the documented agent-loop seam (`POST /v1/host/sample/agentloop/run`) and soft-skip until a host wires it. 2026-05-25 (RFC 0059 — host.workspace M2, reference-host enforcement) added two `workspace-*.test.ts` scenarios: `-behavior` (capability-gated CRUD round-trip / `If-Match` 409 `workspace_conflict` / `workspace_too_large` / §D run-start snapshot, all via the real `/v1/host/workspace/files` §C endpoints) and `-cross-tenant-isolation` (WCT-1 — drives the documented `POST /v1/host/sample/workspace/op` seam to assert a file owned by one `{tenant, workspace}` is unreadable, on both `get` and `list`, under a different owner; backs the new `workspace-cross-tenant-isolation` SECURITY invariant). The in-memory reference host now advertises `capabilities.workspace.supported` and honors §C/§D/§E end-to-end. 2026-05-25 (RFC 0062 — memory.distillation "dreams") added five `distillation-*.test.ts` scenarios: `-shape` (always-on; validates the `capabilities.memory.distillation` block + the additive `distillation` sub-object on `memory.compacted`) plus `-token-budget` (within budget `tokensUsed ≤ tokenBudget`; an un-meetable budget → `token_budget_exceeded` with no partial archive), `-stable-archive` (same sources + budget ⇒ byte-stable archive checksum), `-index-roundtrip` (gated additionally on `indexEmitted`; the `MEMORY-INDEX.json` workspace file is retrievable + `workspace.updated` fired), and `-secret-carryforward` (SR-1: a redacted source secret never appears in the archive) — the four behavioral scenarios drive the documented memory-distillation seam (`POST /v1/host/sample/memory/distill`) and soft-skip until a host wires it. 2026-05-25 (RFC 0063 — core.subWorkflow.outputAttestation) added four `subrun-*.test.ts` scenarios: `-attestation-shape` (always-on; validates the `capabilities.agents.subRunAttestation` flag) plus `-checksum-stable` (the child output checksum is the byte-stable, key-order-invariant RFC 8785 JCS + SHA-256 digest), `-approval-gate` (`requireApproval` → `accept` merges, `reject` does not), and `-approval-fail-closed` (no `accept`/`edit-accept` → no merge; backs the deferred `subrun-merge-approval-fail-closed` invariant) — the three behavioral scenarios drive the documented sub-run attestation seam (`POST /v1/host/sample/subrun/attest`) and soft-skip until a host wires it. 2026-05-25 (RFC 0064 — host.toolHooks) added five `tool-hooks-*.test.ts` scenarios: `-shape` (always-on; validates the `capabilities.toolHooks` block + the optional content-free fields on `agentToolCalled` / `agentToolReturned`) plus `-content-free` (gated on `prePostEvents`), `-authorization-fail-closed` (gated on `perToolAuthorization`), `-rate-limit` (gated on `perToolRateLimit`), and `-secret-redaction` (gated on `prePostEvents` + the SR-1 `argsHash` redaction rule) — the four behavioral scenarios drive the documented tool-hooks invoke seam (`POST /v1/host/sample/toolhooks/invoke`) and soft-skip until a host wires it. 2026-05-25 (RFC 0060 — host.heartbeat) added four `heartbeat-*.test.ts` scenarios: `-capability-shape` (always-on; validates the `capabilities.heartbeat` block) plus `-fires-once-per-tick`, `-idempotent-no-spam`, and `-runtime-bound` (gated on `capabilities.heartbeat.supported` + the host heartbeat tick seam; soft-skip until a host wires it). 2026-05-25 (RFC 0057 — memory write-attribution) added five `memory-attribution-*.test.ts` scenarios: `-shape` (always-on advertisement check on `capabilities.memory.attribution`), plus `-no-content`, `-tenant-scoped`, `-emits-on-write`, and `-replay-stable` (gated on `capabilities.memory.attribution.emitsWriteEvents`) verifying the content-free `memory.written` RunEvent, its two SECURITY invariants (`memory-attribution-no-content` + `memory-attribution-tenant-scoped`), and the §D replay rule that a `replay`-mode fork MUST NOT regenerate `memoryId`. 2026-05-25 (RFC 0025 §C point 1 — test-catalog isolation invariant; pairs with the 25 publish-error scenarios in `pack-registry-publish.test.ts`) added `pack-registry-isolation.test.ts` — capability-gated on `capabilities.packs.testMode.{supported, isolated}: true`; PUTs a disposable pack into `/v1/packs-test/{name}` and asserts the same `(name, version)` does NOT appear via `GET /v1/packs/{name}` — anchors the test-catalog isolation MUST in RFC 0025 §C. 2026-05-25 (RFC 0028 Tier-2 post-promotion T2 — read-side sister scenario for workspace-membership enforcement) added `prompt-read-workspace-membership-enforced.test.ts` — gates on `capabilities.prompts.supported: true` (broader than `mutableLibrary` so read-only hosts that expose `?workspaceId=` are also probed); drives `GET /v1/prompts?workspaceId=<random-non-member>` and interprets the response: 4xx PASS (canonical envelope check on 403); 200 with empty `templates[]` PASS (correct null result for a nonexistent workspace); 200 with non-empty `templates[]` FAIL (cross-tenant leak); 200 without `templates[]` field SKIP (host doesn't expose workspace-scoped reads). Verifies SECURITY invariant `prompt-read-workspace-membership-enforced`. Same-day T1 strengthened `prompt-mutation-workspace-membership-enforced.test.ts` to pin `error === "workspace_membership_required"` when the host's refusal status is 403 (other refusal codes unconstrained). 2026-05-25 (RFC 0028 Tier-2 follow-up — workspace-membership enforcement on mutating prompt endpoints, filed in response to a self-disclosed adopter vulnerability) added `prompt-mutation-workspace-membership-enforced.test.ts` — capability-gated on `capabilities.prompts.mutableLibrary: true`; drives `POST /v1/prompts` with a cryptographically-random non-member `workspaceId` and asserts the host refuses (NOT a 2xx; any 4xx/5xx is acceptable — silent success is the failure mode). Verifies SECURITY invariant `prompt-mutation-workspace-membership-enforced`. 2026-05-22 (RFC 0034 §B follow-up — secret-leakage harness against the OTel + debug-bundle seams) added `secret-leakage-otel-attribute.test.ts` — gates on `capabilities.secrets.supported` + `capabilities.observability.testSeams.{otelScrape,debugBundleExport}` AND the `OPENWOP_CANARY_SECRET_VALUE` env (host operator + conformance runner agree on the canary). Drives the existing `openwop-smoke-byok-roundtrip` fixture end-to-end; scrapes both seams after run completion; hard-fails if the canary plaintext appears in any OTel span attribute or debug-bundle field. Verifies SECURITY invariants `secret-leakage-otel-attribute` + `secret-leakage-debug-bundle-otel`. 2026-05-22 (RFC 0041 Phase 4 — replay determinism under nondeterministic models) added three scenarios: `replay-divergence-at-refusal.test.ts` (advertisement-shape probe on `replayDeterminism.refusalDivergenceEmission` + 2 `it.todo` for the dual-direction refusal-divergence case), `replay-observable-sequence-determinism.test.ts` (capability-gated; behavioral assertion soft-skipped until a `conformance-phase4-nondet-tool` fixture ships), `replay-llm-cache-key-portable.test.ts` (intra-host reproducibility + non-recipe-field invariance + Phase 4 advertisement alignment — reuses the existing `POST /v1/host/sample/test/llm-cache-key` seam from the sibling `replay-llm-cache-key.test.ts`). 2026-05-20 (RFC 0027 §A templateKinds-coverage follow-up — paired with `prompt-end-to-end-events.test.ts`) added `prompt-all-four-kinds-events.test.ts` exercising all four `PromptKind` values (`system`, `user`, `schema-hint`, `few-shot`) end-to-end through the reference workflow-engine sample's `local.sample.demo.mock-ai` dispatch path; capability-gated via `behaviorGate('prompts-supported', ...)`. Closes the credibility gap where the host advertised `templateKinds: ["system", "user", "few-shot", "schema-hint"]` but only the system+user pair was actually wired into dispatch. 2026-05-20 (RFCs 0030–0033 — envelope LLM-contract-hardening track) added 15 scenarios across four `Active` RFCs: `envelope-reasoning-shape.test.ts` (RFC 0030, always-on; asserts the OPTIONAL `reasoning` property on the three universal-kind schemas + the `schema.response` deliberate omission), `envelope-reasoning-secret-redaction.test.ts` (RFC 0030, capability-gated on `capabilities.envelopes.reasoning.supported` + `secrets.supported`; 5 `it.todo()` placeholders for SECURITY invariant `envelope-reasoning-secret-redaction`), `envelope-tier-one-subset-static.test.ts` (RFC 0030, always-on for load-bearing rules — no `oneOf` / `allOf` / `not` / `prefixItems` / `propertyNames` anywhere; gated on `tierOneSubsetCompliance: "strict"` for OpenAI-strict-only constraints), `envelope-variant-discriminator-static.test.ts` (RFC 0031, always-on; asserts no `oneOf` + every `anyOf` branch declares a single-string-enum discriminator in `required` on every `schemas/envelopes/*.schema.json`), `model-capability-substituted.test.ts` (RFC 0031, advertisement-shape probe on `capabilities.modelCapabilities.advertised[]` identifier pattern + 5 `it.todo()` placeholders for SECURITY invariant `model-capability-substituted-no-credential-disclosure`), `model-capability-insufficient.test.ts` (RFC 0031, 6 `it.todo()` placeholders for refusal + no-recursive-fallback), `node-module-required-capabilities-shape.test.ts` (RFC 0031 SHOULD-tier authoring-convention; 4 `it.todo()` placeholders), and the six envelope-reliability events from RFC 0032 (`envelope-retry-attempted` carrying the shared advertisement-shape probe enforcing both MUST-tier events in `events[]` per RFC 0032 §C, plus `envelope-retry-exhausted`, `envelope-refusal-shape`, `envelope-truncated`, `envelope-nl-to-format-engaged`, `envelope-recovery-applied` — collectively 39 `it.todo()` placeholders covering retry/refusal/truncation/recovery + SECURITY invariants `envelope-refusal-no-prompt-leak` and `envelope-recovery-no-content-leak`), plus RFC 0033's two scenarios (`envelope-completion-distinguishes-truncation.test.ts` + `envelope-truncation-cap-exhaustion.test.ts` — 12 `it.todo()` placeholders covering the truncation-vs-schema-violation retry-routing distinction + the DoS-bound assertion). Reference workflow-engine sample advertises `capabilities.envelopes.reasoning: { supported: true, promptDirective: "off" }` + `tierOneSubsetCompliance: "warn"` honestly (schemas accept the field; host doesn't yet inject the directive); the other three RFCs' capability blocks defer to reference-host emission code per the staged RFC 0027 §G precedent. 2026-05-20 (RFC 0028 §B Phase B — prompt-pack boot-time install) added `prompt-pack-install.test.ts` (capability-gated on `capabilities.prompts.endpointsSupported: true`; asserts a host that ran the boot-time pack loader surfaces ≥ 1 pack-source template under `GET /v1/prompts?source=pack` carrying the canonical `meta.source: "pack"` + `meta.packName` + `meta.packVersion` stamps; positively identifies the in-tree `vendor.openwop.prompt-sample` reference pack's `writer-system` template when present). Pairs with the new `host/promptPackLoader.ts` boot-time entry on the reference workflow-engine sample, which scans `examples/packs/*` plus `OPENWOP_PROMPT_PACKS_DIR` and calls `installPackTemplates()` for each `kind: "prompt"` pack found. 2026-05-20 (RFC 0029 Phase C — prompt resolution chain wire shape) added three more scenarios: `prompt-resolution-chain-node-wins.test.ts` (capability-gated on `capabilities.prompts.supported: true`; asserts layer-1 node-config supersedes lower layers per `spec/v1/prompts.md` §"Resolution chain (normative)"), `prompt-resolution-chain-agent-intrinsic.test.ts` (additionally gated on `capabilities.prompts.agentBindings: true`; asserts agent intrinsic `systemPromptRef` wins over `promptOverrides` AND lower layers when the node has no layer-1 ref), `prompt-resolution-chain-fallback-cascade.test.ts` (asserts layer 3 workflow-defaults wins over layer 4 host-defaults; layer 4 host-defaults wins when 1-3 yield null; resolved is null when all four yield null but chain[] still lists every attempted layer). The scenarios drive the host's `POST /v1/host/sample/prompt/resolve` test seam (reference-host implementation deferred to follow-up slice per RFC 0021 staging precedent). 2026-05-20 (RFC 0027 Phase A — prompt templates wire shape) added three scenarios: `prompt-template-shape.test.ts` (always-on; Ajv compileability + positive/negative round-trip for PromptTemplate + PromptRef + PromptKind), `prompt-composed-secret-redaction.test.ts` (capability-gated on `capabilities.prompts.supported: true` + `observability: "full"`; asserts `[REDACTED:<secretId>]` markers in `prompt.composed` payloads for `source: "secret"` variable bindings per SECURITY/threat-model-secret-leakage.md §SR-1), `prompt-composed-trust-marker.test.ts` (same capability gates; asserts `<UNTRUSTED>...</UNTRUSTED>` wrapping + `contentTrust: "untrusted"` propagation per RFC 0020 §D). Paired with new `fixtures/prompt-templates/` sub-directory + per-fixture schema-validity describe block + future SECURITY invariants `prompt-composed-secret-redaction` and `prompt-composed-trust-marker` (lands alongside reference-host emission per RFC 0021 staging precedent). 2026-05-18 (RFC 0022 `Draft` — runtime variable mapping) added four `it.todo()` placeholder scenarios covering the new mapping surfaces on `core.dispatch` (§A — `dispatch-input-mapping.test.ts`, `dispatch-output-mapping.test.ts`, `dispatch-cross-worker-handoff.test.ts`) and `core.subWorkflow` (§B — `subworkflow-input-mapping.test.ts`). Gated on `capabilities.agents.dispatchMapping` (dispatch trio) and `capabilities.subWorkflow.inputMapping` (subWorkflow). Promote to live assertions when RFC 0022 reaches `Active` + a reference host advertises the matching flags. 2026-05-17 (RFC 0003 §D handoff-schema enforcement, HV-1) added `agentPackHandoffSchemaValidation.test.ts` — verifies the host validates dispatch payloads against `handoff.taskSchemaRef` AND return payloads against `handoff.returnSchemaRef` per RFC 0003 §D. Paired with the new `agent-pack-handoff-schema-enforcement` row in `SECURITY/invariants.yaml`. 2026-05-17 (AI Envelope gap-closure, DRAFT v1.x — `spec/v1/ai-envelope.md`) added 7 advertisement-shape scenarios with `it.todo()` behavioral placeholders gated on `capabilities.envelopeContracts.advertised: true`: `aiEnvelope.universalKinds.test.ts`, `aiEnvelope.schemaDrift.test.ts`, `aiEnvelope.correlationReplay.test.ts`, `aiEnvelope.contractRefusal.test.ts`, `aiEnvelope.trustBoundaryPropagation.test.ts`, `aiEnvelope.redaction.test.ts`, `aiEnvelope.capBreached.test.ts`. Paired with the new `envelope-redaction-sr-1-carry-forward` row in `SECURITY/invariants.yaml`. 2026-05-17 (post-publish hardening, deep audit of `core.openwop.agents`) added `agents-run-tool-allowlist.test.ts` — server-free scenario locking in the `core.openwop.agents@1.0.1` safety-fix that closes `OPENWOP-AUDIT-2026-003` (function-typed `tool.handler` properties rejected at `validateTools()` with `INVALID_TOOL_DECLARATION`; tool-driven runs require `ctx.agentRuntime`; tool-less safe fallback preserved). Paired with the new `agents-run-no-raw-handler` row in `SECURITY/invariants.yaml`. Same-day post-publish hardening added `idempotency-key-determinism.test.ts` — server-free scenario locking in the `core.openwop.http@1.1.2` determinism safety-fix (default `composite` mode produces deterministic keys in `(runId, nodeId, payload)`; removed `uuid` mode rejects with `CONFIG_INVALID`; cross-impl vector test lets third-party reimplementations verify wire agreement). Paired with the new `idempotency-key-deterministic` row in `SECURITY/invariants.yaml`. 2026-05-17 (Phase 3 of RFC 0013) added three server-free scenarios exercising the reference workflow-chain expansion library (`conformance/src/lib/workflow-chain-expansion.ts`): `workflow-chain-expansion.test.ts` (parameter substitution + node id collision avoidance + edge rewriting + capability propagation + runtime-invariance contract), `workflow-chain-unresolvable-typeid.test.ts` (rejection with `chain_unresolvable_typeid` when a chain references an unknown typeId), and `workflow-chain-pack-signature-verification.test.ts` (Ed25519 verification recipe reuse from `node-packs.md §Signing`). Earlier that day (Phase 1) added `workflow-chain-pack-manifest-validation.test.ts` — server-free schema-validation scenario covering the new `workflow-chain-pack-manifest.schema.json` (positive sample + two negatives: kind/contents mismatch and invalid `chainId`). Closes RFC 0013 (`Workflow-chain packs`, `Draft`) Phases 1 + 3 alongside the new `spec/v1/workflow-chain-packs.md`, the `Capabilities.workflowChainPacks` block, and the registry build-index/conformance-check `kind` routing from Phase 2. Earlier that day, the suite added 27 `it.todo()` placeholder scenarios paired with RFCs 0014-0020 (host capability surfaces — fs, kvStorage, tableStorage, queueBus, sql/vector/search, blob/cache, mcp.serverMount). These promote to live assertions when each RFC reaches `Active` + the matching capability block lands in `schemas/capabilities.schema.json` + a reference host advertises the capability. Earlier additions include 18 Multi-Agent Shift scenarios (Phases 1-5) added 2026-05-10, the `registry-public.test.ts` public-registry healthcheck added 2026-05-11 (opt-in via `OPENWOP_TEST_PUBLIC_REGISTRY=true`), the `replay-llm-cache-key.test.ts` placeholder added 2026-05-11 (three `it.todo()` cases for the cross-host LLM cache-key recipe per `replay.md` §"LLM cache-key recipe"), the two `production-*.test.ts` scenarios added 2026-05-11 for the `openwop-production` profile per RFC 0009 (`production-backpressure.test.ts`, `production-retention-expiry.test.ts`), the four `auth-*.test.ts` scenarios added 2026-05-11/12 for the production-auth profiles per RFC 0010 (`auth-api-key-rotation.test.ts`, `auth-oauth2-client-credentials.test.ts`, `auth-oidc-user-bearer.test.ts`, `auth-mtls.test.ts` (opt-in via `OPENWOP_TEST_MTLS=1`)), `replay-retention-expiry.test.ts` added 2026-05-12 (capability shape + 410/422 envelope per `replay.md` §"Retention and garbage collection"), `bulk-cancel.test.ts` added 2026-05-12 (Phase B close-out of R1 — `POST /v1/runs:bulk-cancel`), the two Phase H launch-blocker advertisement-contract scenarios added 2026-05-12 (`mcp-toolcall-redaction.test.ts` for the MCP-1 invariant per `host-capabilities.md §host.mcp` + `threat-model-prompt-injection.md §UNTRUSTED`, and `http-client-ssrf.test.ts` for the SSRF + body-size cap advertisement contract on `capabilities.httpClient`), the `wasm-pack-abi-version-rejection.test.ts` Track 7 scenario added 2026-05-12 for the ABI-mismatch positive path via the `vendor.openwop.misbehaving-abi` pack per RFC 0008 §H, the `otel-trace-propagation-subworkflow.test.ts` Track 11 close-out added 2026-05-13 (parent + child run spans share the inbound traceparent's traceId across the `core.subWorkflow` dispatch boundary), and the three RFC 0012 (Memory Compaction Profile, `Active`) scenarios added 2026-05-13/14: `memory-compaction-sr1-carry-forward.test.ts` (load-bearing SR-1 §D), `memory-compaction-event-emitted.test.ts` (canonical §B payload shape), and `memory-compaction-provenance-tag.test.ts` (soft assertion on §C `compacted-from:<id>` convention). All three gate on `capabilities.memory.compaction.supported` + the host's test seam at `/v1/test/memory/{seed,compact}` (Postgres reference host enables both via `OPENWOP_MEMORY_COMPACTION=true OPENWOP_TEST_TRIGGER_COMPACTION=true`). 2026-05-15 (gap-closure CF-3) added `interrupt-token-matrix.test.ts` (malformed / unknown / replay / cross-run-id paths on `GET|POST /v1/interrupts/{token}`). 2026-05-31 (RFC 0078 portable tool catalog + RFC 0079 credential provenance / egress policy — the Active→Accepted behavioral gate) added four: `tool-catalog-projection.test.ts` (capability-gated on `toolCatalog.supported` via `behaviorGate('openwop-tool-catalog', …)` — the NORMATIVE `GET /v1/tools` list with each `ToolDescriptor` schema-valid + `source`/`safetyTier` in the closed vocab + content-free, `GET /v1/tools/{toolId}` round-trip + unknown-id 404, 401-unauthenticated, and the §F-2 cross-principal non-disclosure; black-box, no POST seam), `tool-session-lifecycle.test.ts` (gated on `toolCatalog.sessionLifecycle` — the §D `tool.session.opened`-before / `tool.session.closed`-after bracket over the RFC 0064 call events via the `POST /v1/host/sample/tools/session-run` seam, one shared `sessionId`, content-free), `egress-audience-binding.test.ts` (KEYSTONE — gated on `httpClient.egressPolicy.supported`; the §C confused-deputy MUST via `POST /v1/host/sample/egress/decide`: an out-of-audience egress is denied/downgraded with the credential NOT attached, a provenance-unevaluable egress fails closed — the behavioral leg of `egress-credential-audience-bound`), and `egress-decision-content-free.test.ts` (the SR-1 canary — the credential value never surfaces in `egress.decided` and `reason` stays in the CLOSED vocabulary). The maintained scenario-to-spec map lives in [`coverage.md`](./coverage.md); this README keeps the operator quickstart and the historical scenario notes below.
+The current suite has 365 scenario files under `src/scenarios/`. 2026-06-23 (RFC 0106 — real-time voice session profile, Accept cycle) added six gated behavioral scenarios driving the openwop-app live host (rev `00293-89w`): `voice-transcription-streaming` + `voice-transcription-unadvertised` (the `call-transcriber` seam; the latter gated-by-absence), `voice-synthesis-streaming` (the `stream:true` synthesis arm → metadata-only `voice.synthesis_chunk` events), `voice-bargein-no-partial-leak` (the `/voice/barge-in` seam — `voice.barge_in`→`voice.cancelled` with no chunk after; **graduated `voice-bargein-no-partial-leak` reference-impl→protocol** on the live proof), and `voice-interim-not-durable` + `voice-streamref-tenant-bound` (§F INV-1/INV-4; soft-skip on the §E `transcription_unsupported` / no-live-streamRef path — stay reference-impl until a host with a scripted-interim / live-streamRef arm proves them). 2026-06-23 (RFC 0107 — publishable declarative pack kinds) added one: `registry-declarative-kinds.test.ts` (always-on server-free — the registry version-manifest carries the `kind` discriminator + per-kind declarative payload, `runtime` is conditional on `kind` via `allOf if/then/else`, published artifact-type and connection manifests validate, and a declarative-with-`runtime` or node-without-`runtime` manifest is rejected). 2026-06-23 (RFC 0106 — real-time voice session profile, Phase 2) added one: `voice-event-payloads-shape.test.ts` (always-on server-free — all seven `voice.*` types are in the `RunEventType` enum, each has a payload `$def` via `typeIndex`, `voice.transcript` REQUIRES `contentTrust:"untrusted"` (the schema-enforced half of `voice-transcript-untrusted`), `voice.synthesis_chunk` is metadata-shaped (seq+mimeType required; bytes by `url`/`streamRef`), and the content-free events reject unknown properties). Phase 2 also lands the `voice.*` payload `$defs` in `run-event-payloads.schema.json` + the `asyncapi.yaml` messages + the four §F `SECURITY/invariants.yaml` rows (1 protocol-tier `voice-transcript-untrusted` + 3 reference-impl behavioral, graduating at `Active → Accepted`). The gated behavioral legs (`voice-transcription-streaming`/`-unadvertised`, `voice-synthesis-streaming` + the three behavioral invariant scenarios) land with the reference host at `Active → Accepted`. 2026-06-23 (RFC 0106 — real-time voice session profile, Phase 1) added one: `aiproviders-realtimevoice-shape.test.ts` (always-on server-free — the `aiProviders.realtimeVoice` object advertisement: the four sub-flags `transcription`/`synthesis`/`turnDetection`/`bargeIn` are declared, `realtimeVoice` is absent from `aiProviders.required`, the `turnDetection`/`bargeIn ⇒ transcription` `dependentRequired` closure and the `synthesis ⇒ speechSynthesis` if/then closure hold via Ajv2020, and out-of-enum / boolean sub-flag values are rejected). The gated behavioral legs (`voice-transcription-streaming` / `-unadvertised`, `voice-synthesis-streaming`) and the four §F live-ingress invariant scenarios land in Phase 2 at the `Active → Accepted` cycle. 2026-06-22 (RFC 0101 — multi-party group conversation) added two — `multi-party-conversation-shape.test.ts` (always-on server-free — asserts the three additive RFC 0101 wire facts: a 3-agent council `conversation.opened` participant roster (instance ids) + a user opening turn validates, every `role: 'agent'` turn carrying a roster-instance `speakerId` validates while one OMITTING `speakerId` MUST FAIL schema validation (the `allOf`/`if role==='agent' then required:['speakerId']` conditional), a non-AgentRef participant item is rejected, the `capabilities.multiPartyConversation { supported, maxParticipants? }` block is declared + closed and rejects extras / `maxParticipants:1` / a missing `supported`, and the non-participant membership predicate is asserted server-free) and `multi-party-conversation-behavioral.test.ts` (capability-gated on `multiPartyConversation.supported` via `behaviorGate('openwop-multi-party-conversation', …)` — drives the conformance-only seam `POST /v1/host/sample/conversation/multi-party/{open,exchange}` (`host-sample-test-seams.md`, since RFC 0101 mints no normative client trigger to open a council): a 3-agent council opens and a roster-valid attributed agent turn is accepted, while a `role:'agent'` turn missing `speakerId`, a non-participant `speakerId`, and an over-`maxParticipants` open are each rejected with `error.code:'validation_error'` (status-tolerant 400/422 per RFC 0005 §E); soft-skips on 404/405 — reference impl: the postgres example host). 2026-06-20 (RFC 0105 — speech synthesis adapter) added three: `aiproviders-speechsynth-shape.test.ts` (always-on server-free — the `aiProviders.speechSynthesis` `const "supported"` flag is declared, absent from `aiProviders.required`, and a string-const advertisement validates while the object form `{supported:true}` is rejected), `speech-synthesis-roundtrip.test.ts` (gated on `aiProviders.speechSynthesis === "supported"` via `behaviorGate('openwop-speech-synthesis', …)` — an advertising host's `callSpeechSynthesizer` round-trip via the `POST /v1/host/sample/ai/call-speech-synthesizer` seam returns `audio` with EXACTLY ONE of `url`/`base64`, a non-empty `mimeType`, and the echoed `voiceId`; soft-skips on 404), and `speech-synthesis-unadvertised.test.ts` (gated-by-absence via `behaviorGate('openwop-speech-synthesis-unadvertised', …)` — a host NOT advertising `speechSynthesis` MUST reject the call with `speech_synthesis_unsupported`, never a silent no-op). 2026-06-19 (RFC 0104 — portable HITL approver routing) added one: `interrupt-approver-routing.test.ts` (server-free Ajv2020 — the `interrupt.approverRouting` capability block shape, the additive optionality of `approverGroupRefs` / `approverRoleRefs` / `audience` on the `ApprovalData` schema, the closed `audience` object, and the §"Portable approver routing" `notifyTargets` reference rule that `audience` DEFAULTS to the resolved eligibility union when omitted and OVERRIDES it when present; the capability-gated leg asserts an advertising host's `interrupt.approverRouting` is honest — `refKinds` ⊆ {group, role}, `audience` boolean — and soft-skips when the host does not advertise the capability). 2026-06-17 (RFC 0103 — localized content surface) added one: `localized-content-delivery.test.ts` (server-free Ajv2020 — the four content schemas + the §C `resolveSection` merge + §A capability coherence; the public test for `content-published-cache-no-draft` / `content-response-tenant-scoped` / `content-no-cross-tenant-enumeration`; the live legs gate on `capabilities.content.supported` and soft-skip without a `GET /v1/content/pages/{slug}` target). 2026-06-15 (RFC 0102 — A2UI agent-authored interface surfaces) added five: `a2ui-surface-shape.test.ts` (server-free Ajv2020 — the closed core `ui.a2ui-surface` payload validates, while an out-of-catalog component / extra script-bearing property / unenumerated `catalogVersion` / `action.target` outside `enum["resume","exchange"]` each fail; the structural half of `a2ui-action-confinement` and the enabling precondition for the render-side `a2ui-surface-no-code-exec` / `a2ui-surface-no-network-egress` reference-app probes), `a2ui-surface-degrades.test.ts` (the kind is optional/advertised, not a MUST-recognize universal kind, and an unadvertised kind is gated — N6 — never crashing the run), `a2ui-surface-version-refusal.test.ts` (the enumerated `catalogVersion` rejects an unadvertised version → `unknown_schema_version`, and the surface schema carries no external `$ref`), `a2ui-surface-replay.test.ts` (all `$ref`s internal so a stored surface `:fork`/replays deterministically; same-`correlationId` + divergent `type` → `envelope_correlation_conflict`), and `a2ui-untrusted-blocks-approval.test.ts` (a `meta.contentTrust:'untrusted'` surface is trust-gated and MUST NOT advance an approval interrupt — composition of `untrusted_content_blocks_approval`). The four behavioral legs soft-skip on 404 (host-pending; the `openwop-app` reference renderer is the render-side probe). 2026-06-14 (RFCs 0099/0100 — external-event trigger ingestion + async/durable A2A tasks) added one new scenario (`trigger-ingestion.test.ts`) and extended `a2a-task-roundtrip.test.ts` with the RFC 0100 async subtests: `trigger-ingestion.test.ts` (RFC 0099 — always-on `TriggerEvent` / `TriggerSubscriptionRegistration` schema legs incl. the §F.1 per-source one-of, the `AttachmentRef.ref`-only rule + raw-URL rejection backing `trigger-ingestion-ssrf`, and the content-free `trigger.delivery.attempted` shape backing `trigger-ingestion-content-redaction`; plus a capability-gated behavioral leg on `triggerBridge.ingestion` driving the `POST /v1/host/sample/trigger-bridge/ingest` seam for SSRF refusal + header-redaction), and the `a2a-task-roundtrip.test.ts` additions (RFC 0100 — always-on `A2ATaskState` + `capabilities.a2a` shape legs incl. the lowercase-hyphen state enum, the `PushConfig` `url`-required + truncated-`tokenFingerprint` rule backing `a2a-push-egress-ssrf`, the no-inline-inputs `additionalProperties:false` SR-1 check; plus capability-gated durable-`tasks/get`-after-disconnect and push-SSRF behavioral legs on `a2a.durableTasks` / `a2a.pushNotifications` via the `/v1/host/sample/a2a/tasks/*` seam). 2026-06-13 (RFCs 0096/0097/0098 — reviewable learning, standing goals, agent-platform portability) added three always-on-plus-gated scenarios: `proposal-reviewable-learning.test.ts` (RFC 0096 — the `agents.proposals` shape + the `Proposal` round-trip incl. the dropped `rule` kind + the content-free `proposal.{created,activated}` events, plus a gated apply-without-scope→403 leg; backs `proposal-inert-until-applied` + `proposal-no-resynthesis`), `goal-standing-continuation.test.ts` (RFC 0097 — the `agents.goals` shape + the `Goal` round-trip + the content-free `goal.{evaluated,closed}` events, plus gated bounded-termination→422 + judge-only-completion legs; backs `goal-continuation-bounded` + `goal-completion-judge-only`), and `export-bundle-portability.test.ts` (RFC 0098 — the `portability` shape incl. the `import⇒dryRun` if/then + the `ExportBundle` round-trip rejecting every credential-named field + the content-free `import.applied` event, plus a gated literal-credential-import→422 leg; backs `export-bundle-no-credential-material`). 2026-06-11 (RFCs 0093/0094 — protocol hardening + wire-shape reconciliation) added five: `version-fold.test.ts` (the `version-negotiation.md` §`X-Force-Engine-Version` cross-version matrix through the previously-orphaned `conformance-version-fold` fixture — closes catalog gap F5; soft-skips when `Capabilities.testing.forceEngineVersionRange` is unadvertised), `stream-text-fixture.test.ts` (the `stream-modes.md` §`messages` fold through the deterministic `stream-text` mock provider + the previously-orphaned `conformance-stream-text` fixture — closes catalog gap F1), `i18n-negotiation.test.ts` (gated on `capabilities.i18n` via `behaviorGate('openwop-i18n', …)` — an unsupported or malformed `Accept-Language` never 400s, `Content-Language` reflects the locale actually used, and error `code` strings stay the canonical English tokens), `grpc-transport.test.ts` (gated on `capabilities.grpc` via `behaviorGate('openwop-grpc-transport', …)` — advertisement-shape only per `grpc-transport.md` §Field semantics: `service` MUST be `openwop.v1.Engine`, the `tls` enum, `grpcs?://` endpoint URIs, `supportedTransports` includes `grpc` when exposed, production claimants require `tls: "required"`; no gRPC dialing), and `webhook-tenant-isolation.test.ts` (RFC 0093 §A.3 — backs the new protocol-tier `webhook-cross-tenant-isolation` invariant; a two-tenant proof through the `/v1/host/sample/test/surface` seam plus black-box registration-surface scoping). `spec-corpus-validity.test.ts` also gained the RFC 0094 §A satisfiability probe: canonical `createRun` bodies MUST pass the composed request schema (closed via `unevaluatedProperties: false` at the composition site, never inside an `allOf` branch) and an undeclared property MUST fail. 2026-06-07 (RFCs 0090/0091/0092 — verifier turn + convergence, multimodal perception input, agent capability requirements) added six: the always-on, server-free shape probes `agent-verifier-shape.test.ts`, `aiproviders-input-shape.test.ts`, `agent-requires-capabilities-shape.test.ts`, plus the capability-gated **behavioral** legs `agent-capability-degraded-projection.test.ts` (RFC 0092 §B — the `degraded[]` projection on `GET /v1/agents`, black-box, non-vacuous via `OPENWOP_DEGRADED_CAPABILITY_AGENT_ID`), `callai-multimodal.test.ts` (RFC 0091 §A/§B — advertised modality accepted / unadvertised → `unsupported_modality`, via the `POST /v1/host/sample/ai/call` seam), and `verifier-gating.test.ts` (RFC 0090 §B — a `fail` verdict blocks commit, via the `POST /v1/host/sample/agents/verify-run` seam). The three behavioral legs soft-skip by default and hard-fail under `OPENWOP_REQUIRE_BEHAVIOR=true` — the Active→Accepted reference-host proof for each RFC. 2026-06-02 (RFC 0082 §B — deployment channel resolve-and-pin, production-path coverage) added `agent-channel-dispatch.test.ts` (capability-gated on `agents.deployment.supported` + the seeded `conformance-agent-channel-dispatch` fixture + advertised `replay` mode via `behaviorGate('openwop-deployment-channel-dispatch', …)` — proves the §B pin from a REAL run graph, complementing `agent-deployment-lifecycle.test.ts` Leg 4's host-sample seam: a canonical `POST /v1/runs` of a node binding `agent.channel:"stable"` MUST record `resolvedChannel` + `resolvedAgentVersion` on `agent.invocation.started` (RFC 0077), a `:fork{mode:"replay"}` MUST re-read that recorded version, and the seam-guarded Leg 3 MOVES the channel then asserts a replay STILL carries the original pin — never re-resolving a moved channel; soft-skips by default, hard-fails under `OPENWOP_REQUIRE_BEHAVIOR=true` — the production-path proof of the §B contract). 2026-06-01 (RFC 0085 — `openwop-agent-platform` meta-profile, the Active→Accepted behavioral gate) added `agent-platform-aggregate-evidence.test.ts` (capability-gated on a host CLAIMING `openwop-agent-platform` in its live discovery `profiles[]` via `behaviorGate('openwop-agent-platform', …)` — the §C/§D honest-advertisement rule on the live `/.well-known/openwop`: the claim MUST satisfy the §B floor predicate (`isAgentPlatformPartial` → `partial`/`full`, never `none`), backed by the per-capability evidence not the profile string; `OPENWOP_AGENT_PLATFORM_TIER=full` forces the non-vacuous full bar — all governance terms + tenant installScope + all 16 §D terms; server-requiring, the always-on §B/§D derivation legs stay in `agent-platform-profile.test.ts` — the RFC 0085 → Accepted bar). 2026-06-01 (RFC 0084 — budget, quota + cost policy, the Active→Accepted behavioral gate) added `budget-enforcement.test.ts` (capability-gated on `budget.supported` via `behaviorGate('openwop-budget-enforcement', …)` — the §C/§D enforcement via the new `POST /v1/host/sample/budget/run` seam + the test event-log seam: a `hard-cost-exhaust` run emits the strict-ordered `budget.reserved → budget.consumed → budget.threshold.crossed{percent} → budget.exhausted → cap.breached{kind:"budget-cost"} → run.failed{error:"budget_exhausted"}` chain; a `model-denied` run is refused `budget_model_denied` BEFORE the provider call (fail-closed); an `advisory` host emits the `budget.*` events without stopping; every `budget.*` payload content-free backing `budget-no-pricing-leak`; new lib helper `src/lib/budgetPolicy.ts`; soft-skips on 404 — the RFC 0084 → Accepted bar). 2026-06-01 (RFC 0080 — agent memory capability reconciliation, the Active→Accepted behavioral gate) added `memory-degraded-projection.test.ts` (capability-gated on `agents.manifestRuntime.supported` + `memory.supported` via `behaviorGate('openwop-memory-degraded', …)` — the §C degraded-projection iff-contract on the NORMATIVE `GET /v1/agents`: a degraded inventory entry MUST carry `memoryDegraded:true` + a non-empty, unique `degradedMemoryDimensions[]` from the closed §A-name enum, a non-degraded entry MUST NOT, the inventory is non-empty, and the degraded branch runs non-vacuously when `OPENWOP_DEGRADED_AGENT_ID` names a known-degraded agent; black-box, no POST seam — the RFC 0080 → Accepted bar). This batch also documents the two RFC 0068 conformance seams (`POST /v1/host/sample/memory/consolidate` + `.../commitment/fire`) in `host-sample-test-seams.md` (the 0068 gated scenarios shipped in 1.14.0). 2026-06-01 (RFC 0034 — collector-side BYOK-canary inspection) added `otel-collector-canary-inspection.test.ts` (always-on server-free: stands up a real `OtelCollector`, POSTs synthetic OTLP/HTTP-JSON traces + metrics through its actual ingest path, and proves the new `findCanaryLeakage()` inspector catches a canary embedded in a span attribute / resource attribute / span name / metric data-point attribute while reporting ZERO hits on a redacted payload and never matching an empty canary — the non-vacuous proof that the conformance collector now inspects what the host's OTLP exporter ACTUALLY shipped over the wire, closing the `secret-leakage-otel-attribute` / `-debug-bundle-otel` collector-seam gap; the live capability-gated complement is the new collector-export describe block in `secret-leakage-otel-attribute.test.ts`). 2026-06-01 (RFC 0035 — sandbox wall-clock timeout, the 7th-of-8 graduation) added `sandbox-wasm-timeout.test.ts` (worker-driven server-free: `probeTimeout` in `wasm-sandbox-probe.ts` spawns a worker thread running the committed `misbehaving-timeout.wasm` + a main-thread kill-timer — the thread preemption a same-thread probe can't do — asserting `sandbox_timeout` with a well-behaved positive control; graduates `node-pack-sandbox-timeout` reference-impl→protocol, so 7 of 8 `node-pack-sandbox-*` invariants are now protocol-tier, only the JS-specific `no-eval` permanently exempt). 2026-05-31 (audit-response black-box / graduation batch) added three more: `sandbox-wasm-isolation.test.ts` (RFC 0035 — drives the committed `fixtures/wasm-sandbox/*.wasm` through `wasm-sandbox-probe.ts`: escape/capability-gate via static `WebAssembly.Module.imports()`, an OOB-store memory trap, double-instantiate isolation; 10/10; graduates 6 `node-pack-sandbox-*` invariants reference-impl→protocol), `workspace-cross-tenant-isolation-blackbox.test.ts` (RFC 0059 — two-credential black-box on the normative §C `/v1/host/workspace/files` endpoints: owner A writes, a second-tenant credential fails closed; no seam), and `prompt-resolution-chain-event.test.ts` (RFC 0029 — reads the durable `agent.promptResolved.chain[]` precedence record via the normative `GET /v1/runs/{runId}/events/poll`; no seam) — each the production-path proof that graduates its surface into the `openwop-core-standard` floor. 2026-05-31 (RFC 0088 — the `openwop-core-standard` Core Standard Profile, the audit-response Core Candidate target) added `core-standard-profile.test.ts` (always-on server-free derivation probe: `isCoreStandard` derives the §B floor — `openwop-core` ∧ `openwop-interrupts` ∧ (`openwop-stream-sse` ∨ `openwop-stream-poll`) — a bare `openwop-core` host without interrupts is excluded, a host with no event transport fails, and the annex is absent from `deriveProfiles` because it composes rather than redefines). 2026-05-31 (RFC 0082 — agent deployment lifecycle, the Active→Accepted behavioral gate) added `agent-deployment-lifecycle.test.ts` (capability-gated on `agents.deployment.supported` via `behaviorGate('openwop-deployment-lifecycle', …)` — the §E promotion contract via the new `POST /v1/host/sample/agents/deployment-transition` seam + the test event-log seam across four legs: `promote` (authorize RFC 0049 → approvalGate RFC 0051 → eval-verify RFC 0081 → content-free `deployment.promoted` with a seven-state `toState` + `toVersion`, the record validating `agent-deployment.schema.json`), `unauthorized` (fail-closed — `allowed:false`, no `deployment.promoted`, the behavioral leg of `deployment-promotion-fail-closed`), `eval-gate-unmet` (`eval_gate_unmet` denial, §E-3), and `channel-pin` (the §B `resolvedAgentVersion` recorded-fact on `agent.invocation.started`); new lib helper `src/lib/agentDeployment.ts`; soft-skips on 404 — the RFC 0082 → Accepted bar). 2026-05-31 (RFC 0081 — agent evaluation, the Active→Accepted behavioral gate) added `agent-eval-run.test.ts` (capability-gated on `agents.evalSuite.supported` via `behaviorGate('openwop-eval-run', …)` — the §B `mode:"eval"` projection via the new `POST /v1/host/sample/agents/eval-run` seam + the test event-log seam: `eval.started`-first → one `eval.scored` per task → `eval.completed`-once ordering (count == `eval.completed.taskCount`), the content-free `eval.scored` legs (`score` ∈ 0..1) backing `eval-summary-no-content-leak`, and the NORMATIVE `GET /v1/runs/{runId}/eval-summary` schema-valid `EvalSummary` round-trip with `passedCount <= taskCount`; new lib helper `src/lib/agentEval.ts`; soft-skips on 404 — the RFC 0081 → Accepted bar). 2026-05-31 (RFC 0083 — durable trigger bridge, the Active→Accepted behavioral gate) added `trigger-bridge-delivery.test.ts` (profile-gated on `openwop-trigger-bridge` derived from the live discovery doc — the §C delivery model via the `POST /v1/host/sample/trigger-bridge/deliver` seam + the test event-log seam: dedup→effectively-once `trigger.delivery.attempted{delivered}` (§C-1), retry-exhaustion→`{dead-lettered}` + `trigger.subscription.state.changed{toState:dead-lettered}` (§C-2 + RFC 0053), and the delivered run's `run.started.causationId` == the delivery id (§C / RFC 0040); both `trigger.*` events content-free; the always-on shape stays in `trigger-bridge-shape.test.ts`; new lib helper `src/lib/triggerBridge.ts`). 2026-05-31 (RFC 0087 — agent org-chart, the Active→Accepted behavioral gate) added two capability-gated behavioral scenarios (both gated on `agents.orgChart.supported`, black-box on the normative `/v1/agents/org-chart` surface — no new POST seam): `agent-org-chart-scoping.test.ts` (the `GET /v1/agents/org-chart` tree-shape — departments form an acyclic `parentDepartmentId` tree, members reference `host:<id>` roster entries — + the §D responsibility roll-up via `GET /v1/agents/org-chart/{departmentId}` with a deduped `responsibilities[]` union + the RFC 0074 cross-tenant 404 via `OPENWOP_CROSS_TENANT_ORG_CHART_DEPARTMENT_ID`) and `org-position-no-authority-escalation.test.ts` (the behavioral leg of the protocol-tier invariant — the live org-chart wire carries NO authority-bearing field on any member/department/responsibility-view object; the structural leg stays always-on in `agent-org-chart-shape.test.ts`, and the deeper RFC 0049/0051 authority-invariance legs stay reference-impl tier per the `agent-manifest-runtime` no-host-hook precedent). 2026-05-31 (RFCs 0086 + 0077 — the Active→Accepted behavioral gate) added four capability-gated behavioral scenarios so a non-steward host can be mechanically certified non-vacuously under `OPENWOP_REQUIRE_BEHAVIOR=true`: `agent-roster-attribution.test.ts` (RFC 0086 §B/§C; gated on `agents.roster.supported` — the normative `GET /v1/agents/roster` read shape + `total==roster.length`, the §C `roster.run.initiated`-before-`agent.invocation.started` ordering, the content-free payload backing `roster-attribution-no-content`, the durable work-item `triggerSubscriptionId`, and the RFC 0074 cross-tenant 404 via `OPENWOP_CROSS_TENANT_ROSTER_ID`), `agent-live-invocation-bracket.test.ts` (RFC 0077 §E; gated on `agents.liveRuntime.supported` — `agent.invocation.started`-first / `agent.invocation.completed`-last bracket, matching `invocationId`, `source`/`outcome` closed enums, content-free), `agent-live-structured-output.test.ts` (RFC 0077 §B step 6; gated on `agents.liveRuntime.structuredOutput` — a result violating `handoff.returnSchemaRef` fails the invocation `outcome:"failed"` rather than shipping as completed), and `agent-live-allowlist-enforced.test.ts` (RFC 0077 §F-1 / RFC 0002 §A14; gated on `agents.liveRuntime.supported` — a tool outside `toolAllowlist` is not callable); all four drive the documented `POST /v1/host/sample/roster/fire` + `POST /v1/host/sample/agents/live-invoke` seams plus the test event-log seam and soft-skip on 404 (these are the RFC 0086 / 0077 Active→Accepted bars). 2026-05-30 (RFC 0087 — agent org-chart, Draft -> Active) added `agent-org-chart-shape.test.ts` (always-on server-free: the `capabilities.agents.orgChart` shape + the `AgentOrgChart` round-trip + the non-`host:` member negative + the **§B structural non-authority guarantee** — the schema rejects a `scopes`/`canDispatch`/`permissions`/`authority` field on a member (`additionalProperties:false`), and a member's key set is exactly `{rosterId, departmentId, roleId, reportsTo}` — backing the protocol-tier `org-position-no-authority-escalation` invariant; no new RunEventType). 2026-05-30 (RFC 0086 — standing agent roster, Draft -> Active) added `agent-roster-shape.test.ts` (always-on server-free: the `capabilities.agents.roster` shape + the `AgentRosterEntry` round-trip + the `host:` `rosterId` + `agentRef` version-XOR-channel negatives + the content-free `roster.run.initiated` negatives backing the protocol-tier `roster-attribution-no-content` invariant + the additive `roster` inventory projection + RunEventType-enum membership). 2026-05-30 (RFC 0082 — agent deployment lifecycle, Draft -> Active) added `agent-deployment-shape.test.ts` (always-on server-free: the `capabilities.agents.deployment` shape + the `AgentDeployment` record round-trip + the `AgentRef` `channel` XOR `version` `not`-clause + the four `deployment.*` payloads + the content-free negatives backing the protocol-tier `deployment-event-no-content-leak` invariant). 2026-05-30 (RFC 0085 — `openwop-agent-platform` meta-profile, Draft -> Active) added `agent-platform-profile.test.ts` (always-on server-free derivation of the operational-annex `none`/`partial`/`full` status: all-floor ⇒ partial, missing-flag ⇒ none, the replay-OR-`nondeterminismPolicy.declared` term, floor+governance ⇒ full, missing-tenant-scope ⇒ partial-not-full per the honest-advertisement rule, eval/deploy/budget-are-advisory-not-hard-terms, + the `capabilities.nondeterminismPolicy.declared` shape). 2026-05-30 (RFC 0084 — budget, quota + cost policy, Draft -> Active) added `budget-policy-shape.test.ts` (always-on server-free: `budget-policy.schema.json` round-trip + the §A orthogonality guard — a wall-time field is rejected (it's RFC 0058's `runTimeoutMs`) — + threshold/onExhaustion negatives + the four content-free `budget.{reserved,consumed,threshold.crossed,exhausted}` payloads + the four `cap.breached{budget-*}` kinds + RunEventType-enum membership + the no-pricing-property structural check backing the protocol-tier `budget-no-pricing-leak` invariant + the `capabilities.budget`/`limits.maxBudget*` shape). 2026-05-30 (RFC 0083 — durable trigger + channel bridge, Draft -> Active) added `trigger-bridge-shape.test.ts` (always-on server-free: `trigger-subscription.schema.json` round-trip + missing-`state`/out-of-enum-`source`/unknown-property negatives + the four-state vocab + the two content-free `trigger.{subscription.state.changed,delivery.attempted}` payloads incl. closed `state`/`outcome` enums + RunEventType-enum membership + the `triggerBridge`/`webhooks.durable` capability shape + the `openwop-trigger-bridge` profile derivation incl. the no-dead-letter-sink negative). 2026-05-30 (RFC 0079 — credential provenance + egress policy, Draft -> Active) added `egress-provenance-shape.test.ts` (always-on server-free: `credential-provenance.schema.json` round-trip + `audiences:[]`/missing-`credentialId`/unknown-property negatives + the no-secret-property structural check backing the protocol-tier `egress-decision-no-secret-leak` invariant + the content-free `egress.decided` record incl. the `decision` enum + RunEventType-enum membership + the `httpClient.egressPolicy` shape; the behavioral `egress-credential-audience-bound` confused-deputy MUST is reference-impl tier, deferred to a host). 2026-05-30 (RFC 0078 — portable tool catalog, Draft -> Active) added `tool-descriptor-shape.test.ts` (always-on server-free: `tool-descriptor.schema.json` round-trip + the §C-1 `exec` ⇒ `host-extension` cross-field MUST (RFC 0069) + the `safetyTier`-required negative + `additionalProperties:false`, the `capabilities.toolCatalog` `supported`/`sources`/`sessionLifecycle` shape, and the two content-free `tool.session.{opened,closed}` payload $defs incl. the closed `outcome` enum + RunEventType-enum membership). 2026-05-30 (RFC 0080 — agent memory capability reconciliation, Draft -> Active) added `memory-capability-model-shape.test.ts` (always-on server-free: the additive `capabilities.memory.{writable,search,retention}` dimension shapes + malformed-instance negatives — `retention.ttl` non-boolean, out-of-enum `search.modes`, unknown property under `additionalProperties:false` — the `agent-inventory-response` `memoryDegraded`/`degradedMemoryDimensions` closed-enum fields, and the `openwop-memory` derivation surfacing for read/write + long-term hosts while withholding from `writable:false`). 2026-05-30 (RFC 0081 — agent evaluation, Draft -> Active) added `agent-eval-suite-shape.test.ts` (always-on server-free: the `capabilities.agents.evalSuite` shape + the `AgentEvalSuite`/`EvalSummary` schema round-trips + the three `eval.{started,scored,completed}` payloads + the content-free negatives — a task entry with a `taskOutput` body, a `safetyFinding` with an `excerpt` — backing the new `eval-summary-no-content-leak` SECURITY invariant). 2026-05-29 (RFC 0076 §B — `ctx.http.safeFetch` live-run audit) added `safefetch-live-audit.test.ts` (`behaviorGate('openwop-safefetch-live-audit', …)`, gated on `httpClient.safeFetch` + `toolHooks.prePostEvents`) — asserts the audit-when-both MUST against the **durable run event log** via the new `POST /v1/host/sample/http/safe-fetch-run` open seam + the test event-log seam, closing the seam-vs-production gap (a production `createSafeFetch()` with no audit hooks passes the inline `safefetch-behavior.test.ts` but FAILS this under `OPENWOP_REQUIRE_BEHAVIOR=true`); this is the RFC 0076 §B → Accepted bar; run seam soft-skips on 404 (host-pending). 2026-05-29 (RFC 0066 — `x-openwop-form` picker UX hints, Draft → Active) added `x-openwop-form-pack-manifest.test.ts` (always-on server-free: an annotated `configSchema` stays a valid 2020-12 schema + the advisory hints don't change what it accepts, each §A annotation matches the shape, an unknown `kind` validates for forward-compat, 3 negatives — missing/non-string `kind`, non-string `dependsOn`). 2026-05-29 (RFC 0076 §B — `ctx.http.safeFetch`) added `safefetch-behavior.test.ts` (seam-gated: SSRF block / DNS-rebinding / `Connection: upgrade` refusal / tool-hooks audit-when-both, via `POST /v1/host/sample/http/safe-fetch`; advertisement contract stays in `http-client-ssrf.test.ts`). 2026-05-29 (RFC 0076 §A — pack `runtime.requires[]` install gate) added two: `runtime-requires-shape.test.ts` (server-free closed-vocabulary validation — the 8 tokens validate, a raw builtin name is rejected, empty-array≡omission, `uniqueItems`) + `runtime-requires-install-gate.test.ts` (seam-gated install-grant / install-refuse → `pack_runtime_requirement_unmet` / non-sandbox SHOULD-projection, soft-skip on 404 via `POST /v1/host/sample/packs/install-gate`). 2026-05-29 (RFC 0047 — `host.oauth` authorization-code roundtrip) added `oauth-authorization-code-roundtrip.test.ts` — capability-gated on `capabilities.oauth.supported` + `grants` including `authorization_code`; drives the `POST /v1/host/sample/oauth/authorize-code-roundtrip` seam against the one canonical synthetic provider in `fixtures/oauth-providers/synthetic.json` (soft-skip on 404, Tier-2 host-pending), asserting a successful grant returns a credential REFERENCE (token persisted as a `host.credentials` entry) and that the authorization code / state / PKCE verifier / acquired access+refresh tokens never appear on any run-visible surface (RFC 0047 §C + §C.2 / `credential-payload-redaction`). Closes the RFC 0047 Tier-2 gap (capability-shape + redaction scenarios existed; the actual authorization-code dance was unexercised). 2026-05-26 (RFC 0070 — agent-manifest runtime) added `agent-manifest-runtime.test.ts`; 2026-05-26 (RFC 0071 — artifact-type + chat card packs) added six: `artifact-type-pack-manifest-validation.test.ts` + `artifact-schema-compile-bounded.test.ts` (server-free) + `artifact-type-pack-install.test.ts` + `artifact-type-store-without-render.test.ts` + `chat-card-pack-manifest-validation.test.ts` (server-free) + `chat-card-pack-execution.test.ts` (capability-gated, host-pending). 2026-05-26 (RFCs 0067 / 0068 / 0069 — spec-gap Draft cohort) added five scenarios: `byok-auth-modes.test.ts` (RFC 0067; always-on schema-shape of `aiProviders.authModes` + a discovery-gated §B auth-mode-contract cross-field check), `memory-consolidation-shape.test.ts` (RFC 0068; always-on shape of `agents.memoryConsolidation`/`agents.commitments` + the `agent.memory.consolidated`/`commitment.fired` payload $defs), `memory-consolidation-idempotent.test.ts` + `commitment-fired.test.ts` (RFC 0068; capability-gated behavioral, soft-skip on the documented `/v1/host/sample/memory/consolidate` + `/commitment/fire` seams), and `exec-not-protocol-tier.test.ts` (RFC 0069; always-on server-free structural assertion that the protocol corpus defines no `core.*`/`openwop.*` exec-class primitive — backs the `exec-must-not-be-protocol-tier` SECURITY invariant). 2026-05-25 (RFC 0061 — stateful agent-loop lifecycle, executionModel.version 5) added four `agent-loop-*.test.ts` scenarios: `-version5-shape` (always-on; validates `executionModel.statefulResume`/`transcriptWindow` + the 1–5 version ceiling) plus `-iteration-monotonic` (gated on `version >= 5`; `runOrchestrator.decided.iteration` increments 1,2,3… exactly once per turn), `-workspace-snapshot` (gated additionally on `host.workspace.supported`; a turn-i workspace write is invisible to turn i, visible to turn i+1), and `-stateful-resume` (gated on `statefulResume`; a mid-loop suspend resumes at the same iteration without resetting the counter) — the three behavioral scenarios drive the documented agent-loop seam (`POST /v1/host/sample/agentloop/run`) and soft-skip until a host wires it. 2026-05-25 (RFC 0059 — host.workspace M2, reference-host enforcement) added two `workspace-*.test.ts` scenarios: `-behavior` (capability-gated CRUD round-trip / `If-Match` 409 `workspace_conflict` / `workspace_too_large` / §D run-start snapshot, all via the real `/v1/host/workspace/files` §C endpoints) and `-cross-tenant-isolation` (WCT-1 — drives the documented `POST /v1/host/sample/workspace/op` seam to assert a file owned by one `{tenant, workspace}` is unreadable, on both `get` and `list`, under a different owner; backs the new `workspace-cross-tenant-isolation` SECURITY invariant). The in-memory reference host now advertises `capabilities.workspace.supported` and honors §C/§D/§E end-to-end. 2026-05-25 (RFC 0062 — memory.distillation "dreams") added five `distillation-*.test.ts` scenarios: `-shape` (always-on; validates the `capabilities.memory.distillation` block + the additive `distillation` sub-object on `memory.compacted`) plus `-token-budget` (within budget `tokensUsed ≤ tokenBudget`; an un-meetable budget → `token_budget_exceeded` with no partial archive), `-stable-archive` (same sources + budget ⇒ byte-stable archive checksum), `-index-roundtrip` (gated additionally on `indexEmitted`; the `MEMORY-INDEX.json` workspace file is retrievable + `workspace.updated` fired), and `-secret-carryforward` (SR-1: a redacted source secret never appears in the archive) — the four behavioral scenarios drive the documented memory-distillation seam (`POST /v1/host/sample/memory/distill`) and soft-skip until a host wires it. 2026-05-25 (RFC 0063 — core.subWorkflow.outputAttestation) added four `subrun-*.test.ts` scenarios: `-attestation-shape` (always-on; validates the `capabilities.agents.subRunAttestation` flag) plus `-checksum-stable` (the child output checksum is the byte-stable, key-order-invariant RFC 8785 JCS + SHA-256 digest), `-approval-gate` (`requireApproval` → `accept` merges, `reject` does not), and `-approval-fail-closed` (no `accept`/`edit-accept` → no merge; backs the deferred `subrun-merge-approval-fail-closed` invariant) — the three behavioral scenarios drive the documented sub-run attestation seam (`POST /v1/host/sample/subrun/attest`) and soft-skip until a host wires it. 2026-05-25 (RFC 0064 — host.toolHooks) added five `tool-hooks-*.test.ts` scenarios: `-shape` (always-on; validates the `capabilities.toolHooks` block + the optional content-free fields on `agentToolCalled` / `agentToolReturned`) plus `-content-free` (gated on `prePostEvents`), `-authorization-fail-closed` (gated on `perToolAuthorization`), `-rate-limit` (gated on `perToolRateLimit`), and `-secret-redaction` (gated on `prePostEvents` + the SR-1 `argsHash` redaction rule) — the four behavioral scenarios drive the documented tool-hooks invoke seam (`POST /v1/host/sample/toolhooks/invoke`) and soft-skip until a host wires it. 2026-05-25 (RFC 0060 — host.heartbeat) added four `heartbeat-*.test.ts` scenarios: `-capability-shape` (always-on; validates the `capabilities.heartbeat` block) plus `-fires-once-per-tick`, `-idempotent-no-spam`, and `-runtime-bound` (gated on `capabilities.heartbeat.supported` + the host heartbeat tick seam; soft-skip until a host wires it). 2026-05-25 (RFC 0057 — memory write-attribution) added five `memory-attribution-*.test.ts` scenarios: `-shape` (always-on advertisement check on `capabilities.memory.attribution`), plus `-no-content`, `-tenant-scoped`, `-emits-on-write`, and `-replay-stable` (gated on `capabilities.memory.attribution.emitsWriteEvents`) verifying the content-free `memory.written` RunEvent, its two SECURITY invariants (`memory-attribution-no-content` + `memory-attribution-tenant-scoped`), and the §D replay rule that a `replay`-mode fork MUST NOT regenerate `memoryId`. 2026-05-25 (RFC 0025 §C point 1 — test-catalog isolation invariant; pairs with the 25 publish-error scenarios in `pack-registry-publish.test.ts`) added `pack-registry-isolation.test.ts` — capability-gated on `capabilities.packs.testMode.{supported, isolated}: true`; PUTs a disposable pack into `/v1/packs-test/{name}` and asserts the same `(name, version)` does NOT appear via `GET /v1/packs/{name}` — anchors the test-catalog isolation MUST in RFC 0025 §C. 2026-05-25 (RFC 0028 Tier-2 post-promotion T2 — read-side sister scenario for workspace-membership enforcement) added `prompt-read-workspace-membership-enforced.test.ts` — gates on `capabilities.prompts.supported: true` (broader than `mutableLibrary` so read-only hosts that expose `?workspaceId=` are also probed); drives `GET /v1/prompts?workspaceId=<random-non-member>` and interprets the response: 4xx PASS (canonical envelope check on 403); 200 with empty `templates[]` PASS (correct null result for a nonexistent workspace); 200 with non-empty `templates[]` FAIL (cross-tenant leak); 200 without `templates[]` field SKIP (host doesn't expose workspace-scoped reads). Verifies SECURITY invariant `prompt-read-workspace-membership-enforced`. Same-day T1 strengthened `prompt-mutation-workspace-membership-enforced.test.ts` to pin `error === "workspace_membership_required"` when the host's refusal status is 403 (other refusal codes unconstrained). 2026-05-25 (RFC 0028 Tier-2 follow-up — workspace-membership enforcement on mutating prompt endpoints, filed in response to a self-disclosed adopter vulnerability) added `prompt-mutation-workspace-membership-enforced.test.ts` — capability-gated on `capabilities.prompts.mutableLibrary: true`; drives `POST /v1/prompts` with a cryptographically-random non-member `workspaceId` and asserts the host refuses (NOT a 2xx; any 4xx/5xx is acceptable — silent success is the failure mode). Verifies SECURITY invariant `prompt-mutation-workspace-membership-enforced`. 2026-05-22 (RFC 0034 §B follow-up — secret-leakage harness against the OTel + debug-bundle seams) added `secret-leakage-otel-attribute.test.ts` — gates on `capabilities.secrets.supported` + `capabilities.observability.testSeams.{otelScrape,debugBundleExport}` AND the `OPENWOP_CANARY_SECRET_VALUE` env (host operator + conformance runner agree on the canary). Drives the existing `openwop-smoke-byok-roundtrip` fixture end-to-end; scrapes both seams after run completion; hard-fails if the canary plaintext appears in any OTel span attribute or debug-bundle field. Verifies SECURITY invariants `secret-leakage-otel-attribute` + `secret-leakage-debug-bundle-otel`. 2026-05-22 (RFC 0041 Phase 4 — replay determinism under nondeterministic models) added three scenarios: `replay-divergence-at-refusal.test.ts` (advertisement-shape probe on `replayDeterminism.refusalDivergenceEmission` + 2 `it.todo` for the dual-direction refusal-divergence case), `replay-observable-sequence-determinism.test.ts` (capability-gated; behavioral assertion soft-skipped until a `conformance-phase4-nondet-tool` fixture ships), `replay-llm-cache-key-portable.test.ts` (intra-host reproducibility + non-recipe-field invariance + Phase 4 advertisement alignment — reuses the existing `POST /v1/host/sample/test/llm-cache-key` seam from the sibling `replay-llm-cache-key.test.ts`). 2026-05-20 (RFC 0027 §A templateKinds-coverage follow-up — paired with `prompt-end-to-end-events.test.ts`) added `prompt-all-four-kinds-events.test.ts` exercising all four `PromptKind` values (`system`, `user`, `schema-hint`, `few-shot`) end-to-end through the reference workflow-engine sample's `local.sample.demo.mock-ai` dispatch path; capability-gated via `behaviorGate('prompts-supported', ...)`. Closes the credibility gap where the host advertised `templateKinds: ["system", "user", "few-shot", "schema-hint"]` but only the system+user pair was actually wired into dispatch. 2026-05-20 (RFCs 0030–0033 — envelope LLM-contract-hardening track) added 15 scenarios across four `Active` RFCs: `envelope-reasoning-shape.test.ts` (RFC 0030, always-on; asserts the OPTIONAL `reasoning` property on the three universal-kind schemas + the `schema.response` deliberate omission), `envelope-reasoning-secret-redaction.test.ts` (RFC 0030, capability-gated on `capabilities.envelopes.reasoning.supported` + `secrets.supported`; 5 `it.todo()` placeholders for SECURITY invariant `envelope-reasoning-secret-redaction`), `envelope-tier-one-subset-static.test.ts` (RFC 0030, always-on for load-bearing rules — no `oneOf` / `allOf` / `not` / `prefixItems` / `propertyNames` anywhere; gated on `tierOneSubsetCompliance: "strict"` for OpenAI-strict-only constraints), `envelope-variant-discriminator-static.test.ts` (RFC 0031, always-on; asserts no `oneOf` + every `anyOf` branch declares a single-string-enum discriminator in `required` on every `schemas/envelopes/*.schema.json`), `model-capability-substituted.test.ts` (RFC 0031, advertisement-shape probe on `capabilities.modelCapabilities.advertised[]` identifier pattern + 5 `it.todo()` placeholders for SECURITY invariant `model-capability-substituted-no-credential-disclosure`), `model-capability-insufficient.test.ts` (RFC 0031, 6 `it.todo()` placeholders for refusal + no-recursive-fallback), `node-module-required-capabilities-shape.test.ts` (RFC 0031 SHOULD-tier authoring-convention; 4 `it.todo()` placeholders), and the six envelope-reliability events from RFC 0032 (`envelope-retry-attempted` carrying the shared advertisement-shape probe enforcing both MUST-tier events in `events[]` per RFC 0032 §C, plus `envelope-retry-exhausted`, `envelope-refusal-shape`, `envelope-truncated`, `envelope-nl-to-format-engaged`, `envelope-recovery-applied` — collectively 39 `it.todo()` placeholders covering retry/refusal/truncation/recovery + SECURITY invariants `envelope-refusal-no-prompt-leak` and `envelope-recovery-no-content-leak`), plus RFC 0033's two scenarios (`envelope-completion-distinguishes-truncation.test.ts` + `envelope-truncation-cap-exhaustion.test.ts` — 12 `it.todo()` placeholders covering the truncation-vs-schema-violation retry-routing distinction + the DoS-bound assertion). Reference workflow-engine sample advertises `capabilities.envelopes.reasoning: { supported: true, promptDirective: "off" }` + `tierOneSubsetCompliance: "warn"` honestly (schemas accept the field; host doesn't yet inject the directive); the other three RFCs' capability blocks defer to reference-host emission code per the staged RFC 0027 §G precedent. 2026-05-20 (RFC 0028 §B Phase B — prompt-pack boot-time install) added `prompt-pack-install.test.ts` (capability-gated on `capabilities.prompts.endpointsSupported: true`; asserts a host that ran the boot-time pack loader surfaces ≥ 1 pack-source template under `GET /v1/prompts?source=pack` carrying the canonical `meta.source: "pack"` + `meta.packName` + `meta.packVersion` stamps; positively identifies the in-tree `vendor.openwop.prompt-sample` reference pack's `writer-system` template when present). Pairs with the new `host/promptPackLoader.ts` boot-time entry on the reference workflow-engine sample, which scans `examples/packs/*` plus `OPENWOP_PROMPT_PACKS_DIR` and calls `installPackTemplates()` for each `kind: "prompt"` pack found. 2026-05-20 (RFC 0029 Phase C — prompt resolution chain wire shape) added three more scenarios: `prompt-resolution-chain-node-wins.test.ts` (capability-gated on `capabilities.prompts.supported: true`; asserts layer-1 node-config supersedes lower layers per `spec/v1/prompts.md` §"Resolution chain (normative)"), `prompt-resolution-chain-agent-intrinsic.test.ts` (additionally gated on `capabilities.prompts.agentBindings: true`; asserts agent intrinsic `systemPromptRef` wins over `promptOverrides` AND lower layers when the node has no layer-1 ref), `prompt-resolution-chain-fallback-cascade.test.ts` (asserts layer 3 workflow-defaults wins over layer 4 host-defaults; layer 4 host-defaults wins when 1-3 yield null; resolved is null when all four yield null but chain[] still lists every attempted layer). The scenarios drive the host's `POST /v1/host/sample/prompt/resolve` test seam (reference-host implementation deferred to follow-up slice per RFC 0021 staging precedent). 2026-05-20 (RFC 0027 Phase A — prompt templates wire shape) added three scenarios: `prompt-template-shape.test.ts` (always-on; Ajv compileability + positive/negative round-trip for PromptTemplate + PromptRef + PromptKind), `prompt-composed-secret-redaction.test.ts` (capability-gated on `capabilities.prompts.supported: true` + `observability: "full"`; asserts `[REDACTED:<secretId>]` markers in `prompt.composed` payloads for `source: "secret"` variable bindings per SECURITY/threat-model-secret-leakage.md §SR-1), `prompt-composed-trust-marker.test.ts` (same capability gates; asserts `<UNTRUSTED>...</UNTRUSTED>` wrapping + `contentTrust: "untrusted"` propagation per RFC 0020 §D). Paired with new `fixtures/prompt-templates/` sub-directory + per-fixture schema-validity describe block + future SECURITY invariants `prompt-composed-secret-redaction` and `prompt-composed-trust-marker` (lands alongside reference-host emission per RFC 0021 staging precedent). 2026-05-18 (RFC 0022 `Draft` — runtime variable mapping) added four `it.todo()` placeholder scenarios covering the new mapping surfaces on `core.dispatch` (§A — `dispatch-input-mapping.test.ts`, `dispatch-output-mapping.test.ts`, `dispatch-cross-worker-handoff.test.ts`) and `core.subWorkflow` (§B — `subworkflow-input-mapping.test.ts`). Gated on `capabilities.agents.dispatchMapping` (dispatch trio) and `capabilities.subWorkflow.inputMapping` (subWorkflow). Promote to live assertions when RFC 0022 reaches `Active` + a reference host advertises the matching flags. 2026-05-17 (RFC 0003 §D handoff-schema enforcement, HV-1) added `agentPackHandoffSchemaValidation.test.ts` — verifies the host validates dispatch payloads against `handoff.taskSchemaRef` AND return payloads against `handoff.returnSchemaRef` per RFC 0003 §D. Paired with the new `agent-pack-handoff-schema-enforcement` row in `SECURITY/invariants.yaml`. 2026-05-17 (AI Envelope gap-closure, DRAFT v1.x — `spec/v1/ai-envelope.md`) added 7 advertisement-shape scenarios with `it.todo()` behavioral placeholders gated on `capabilities.envelopeContracts.advertised: true`: `aiEnvelope.universalKinds.test.ts`, `aiEnvelope.schemaDrift.test.ts`, `aiEnvelope.correlationReplay.test.ts`, `aiEnvelope.contractRefusal.test.ts`, `aiEnvelope.trustBoundaryPropagation.test.ts`, `aiEnvelope.redaction.test.ts`, `aiEnvelope.capBreached.test.ts`. Paired with the new `envelope-redaction-sr-1-carry-forward` row in `SECURITY/invariants.yaml`. 2026-05-17 (post-publish hardening, deep audit of `core.openwop.agents`) added `agents-run-tool-allowlist.test.ts` — server-free scenario locking in the `core.openwop.agents@1.0.1` safety-fix that closes `OPENWOP-AUDIT-2026-003` (function-typed `tool.handler` properties rejected at `validateTools()` with `INVALID_TOOL_DECLARATION`; tool-driven runs require `ctx.agentRuntime`; tool-less safe fallback preserved). Paired with the new `agents-run-no-raw-handler` row in `SECURITY/invariants.yaml`. Same-day post-publish hardening added `idempotency-key-determinism.test.ts` — server-free scenario locking in the `core.openwop.http@1.1.2` determinism safety-fix (default `composite` mode produces deterministic keys in `(runId, nodeId, payload)`; removed `uuid` mode rejects with `CONFIG_INVALID`; cross-impl vector test lets third-party reimplementations verify wire agreement). Paired with the new `idempotency-key-deterministic` row in `SECURITY/invariants.yaml`. 2026-05-17 (Phase 3 of RFC 0013) added three server-free scenarios exercising the reference workflow-chain expansion library (`conformance/src/lib/workflow-chain-expansion.ts`): `workflow-chain-expansion.test.ts` (parameter substitution + node id collision avoidance + edge rewriting + capability propagation + runtime-invariance contract), `workflow-chain-unresolvable-typeid.test.ts` (rejection with `chain_unresolvable_typeid` when a chain references an unknown typeId), and `workflow-chain-pack-signature-verification.test.ts` (Ed25519 verification recipe reuse from `node-packs.md §Signing`). Earlier that day (Phase 1) added `workflow-chain-pack-manifest-validation.test.ts` — server-free schema-validation scenario covering the new `workflow-chain-pack-manifest.schema.json` (positive sample + two negatives: kind/contents mismatch and invalid `chainId`). Closes RFC 0013 (`Workflow-chain packs`, `Draft`) Phases 1 + 3 alongside the new `spec/v1/workflow-chain-packs.md`, the `Capabilities.workflowChainPacks` block, and the registry build-index/conformance-check `kind` routing from Phase 2. Earlier that day, the suite added 27 `it.todo()` placeholder scenarios paired with RFCs 0014-0020 (host capability surfaces — fs, kvStorage, tableStorage, queueBus, sql/vector/search, blob/cache, mcp.serverMount). These promote to live assertions when each RFC reaches `Active` + the matching capability block lands in `schemas/capabilities.schema.json` + a reference host advertises the capability. Earlier additions include 18 Multi-Agent Shift scenarios (Phases 1-5) added 2026-05-10, the `registry-public.test.ts` public-registry healthcheck added 2026-05-11 (opt-in via `OPENWOP_TEST_PUBLIC_REGISTRY=true`), the `replay-llm-cache-key.test.ts` placeholder added 2026-05-11 (three `it.todo()` cases for the cross-host LLM cache-key recipe per `replay.md` §"LLM cache-key recipe"), the two `production-*.test.ts` scenarios added 2026-05-11 for the `openwop-production` profile per RFC 0009 (`production-backpressure.test.ts`, `production-retention-expiry.test.ts`), the four `auth-*.test.ts` scenarios added 2026-05-11/12 for the production-auth profiles per RFC 0010 (`auth-api-key-rotation.test.ts`, `auth-oauth2-client-credentials.test.ts`, `auth-oidc-user-bearer.test.ts`, `auth-mtls.test.ts` (opt-in via `OPENWOP_TEST_MTLS=1`)), `replay-retention-expiry.test.ts` added 2026-05-12 (capability shape + 410/422 envelope per `replay.md` §"Retention and garbage collection"), `bulk-cancel.test.ts` added 2026-05-12 (Phase B close-out of R1 — `POST /v1/runs:bulk-cancel`), the two Phase H launch-blocker advertisement-contract scenarios added 2026-05-12 (`mcp-toolcall-redaction.test.ts` for the MCP-1 invariant per `host-capabilities.md §host.mcp` + `threat-model-prompt-injection.md §UNTRUSTED`, and `http-client-ssrf.test.ts` for the SSRF + body-size cap advertisement contract on `capabilities.httpClient`), the `wasm-pack-abi-version-rejection.test.ts` Track 7 scenario added 2026-05-12 for the ABI-mismatch positive path via the `vendor.openwop.misbehaving-abi` pack per RFC 0008 §H, the `otel-trace-propagation-subworkflow.test.ts` Track 11 close-out added 2026-05-13 (parent + child run spans share the inbound traceparent's traceId across the `core.subWorkflow` dispatch boundary), and the three RFC 0012 (Memory Compaction Profile, `Active`) scenarios added 2026-05-13/14: `memory-compaction-sr1-carry-forward.test.ts` (load-bearing SR-1 §D), `memory-compaction-event-emitted.test.ts` (canonical §B payload shape), and `memory-compaction-provenance-tag.test.ts` (soft assertion on §C `compacted-from:<id>` convention). All three gate on `capabilities.memory.compaction.supported` + the host's test seam at `/v1/test/memory/{seed,compact}` (Postgres reference host enables both via `OPENWOP_MEMORY_COMPACTION=true OPENWOP_TEST_TRIGGER_COMPACTION=true`). 2026-05-15 (gap-closure CF-3) added `interrupt-token-matrix.test.ts` (malformed / unknown / replay / cross-run-id paths on `GET|POST /v1/interrupts/{token}`). 2026-05-31 (RFC 0078 portable tool catalog + RFC 0079 credential provenance / egress policy — the Active→Accepted behavioral gate) added four: `tool-catalog-projection.test.ts` (capability-gated on `toolCatalog.supported` via `behaviorGate('openwop-tool-catalog', …)` — the NORMATIVE `GET /v1/tools` list with each `ToolDescriptor` schema-valid + `source`/`safetyTier` in the closed vocab + content-free, `GET /v1/tools/{toolId}` round-trip + unknown-id 404, 401-unauthenticated, and the §F-2 cross-principal non-disclosure; black-box, no POST seam), `tool-session-lifecycle.test.ts` (gated on `toolCatalog.sessionLifecycle` — the §D `tool.session.opened`-before / `tool.session.closed`-after bracket over the RFC 0064 call events via the `POST /v1/host/sample/tools/session-run` seam, one shared `sessionId`, content-free), `egress-audience-binding.test.ts` (KEYSTONE — gated on `httpClient.egressPolicy.supported`; the §C confused-deputy MUST via `POST /v1/host/sample/egress/decide`: an out-of-audience egress is denied/downgraded with the credential NOT attached, a provenance-unevaluable egress fails closed — the behavioral leg of `egress-credential-audience-bound`), and `egress-decision-content-free.test.ts` (the SR-1 canary — the credential value never surfaces in `egress.decided` and `reason` stays in the CLOSED vocabulary). The maintained scenario-to-spec map lives in [`coverage.md`](./coverage.md); this README keeps the operator quickstart and the historical scenario notes below.
 High-level coverage includes:
@@ -171,7 +171,7 @@ Server-required (added in 1.7.0):
 | ------------- | ----------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | **Redaction** | [`capabilities.md`](../spec/v1/capabilities.md) §"Secrets" + NFR-7 + §"aiProviders" | Vendor-neutral assertions that the server doesn't leak secret material. Three scenario groups: (a) discovery shape contract — `secrets` + `aiProviders` advertisements are well-formed regardless of `secrets.supported`; when `supported === true`, scopes MUST be non-empty + `resolution === 'host-managed'`; `byok ⊆ supported`. (b) bearer-token redaction — invalid Bearer canary in `Authorization` header is not echoed in the 401 response body. (c) credentialRef echo control — gated on `secrets.supported === true`; canary planted in `configurable.ai.credentialRef` MUST NOT appear in any RunEvent payload (poll-based capture; transport-agnostic). Uses runtime-built canary fixtures (`lib/canaries.ts`) that defeat static secret scanners. 6 scenarios. |
-Current source tree: 359 scenario files. Use [`coverage.md`](./coverage.md) for current grade/gap tracking.
+Current source tree: 365 scenario files. Use [`coverage.md`](./coverage.md) for current grade/gap tracking.
 ## Remaining Gaps

package/package.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "name": "@openwop/openwop-conformance",
-  "version": "1.33.0",
+  "version": "1.34.0",
   "description": "Production-ready black-box conformance suite for OpenWOP v1.0 compliant servers.",
   "repository": {
     "type": "git",

package/src/scenarios/voice-bargein-no-partial-leak.test.ts ADDED Viewed

@@ -0,0 +1,61 @@
+/**
+ * Barge-in: no partial-output leak (RFC 0106 §F INV-3) — behavioral.
+ *
+ * Backs the protocol-tier SECURITY invariant `voice-bargein-no-partial-leak`.
+ * Gated on `capabilities.aiProviders.realtimeVoice.bargeIn === 'supported'`.
+ * Soft-skips when unadvertised (default) / hard-fails under
+ * `OPENWOP_REQUIRE_BEHAVIOR=true`. Drives `POST /v1/host/sample/voice/barge-in`
+ * (soft-skips on 404):
+ *
+ *   - the host MUST emit `voice.barge_in` then `voice.cancelled` (distinct events);
+ *   - NO `voice.synthesis_chunk` (nor any partial tool/model output) may appear
+ *     AFTER the `voice.cancelled` — a cancellation is all-or-nothing and MUST NOT
+ *     leak the un-guardrailed partial the end-of-turn pass would otherwise scrub.
+ *
+ * Spec references:
+ *   - https://github.com/openwop/openwop/blob/main/RFCS/0106-realtime-voice-session-profile.md (§F INV-3)
+ *   - https://github.com/openwop/openwop/blob/main/SECURITY/invariants.yaml (voice-bargein-no-partial-leak)
+ */
+import { describe, it, expect } from 'vitest';
+import { driver } from '../lib/driver.js';
+import { behaviorGate } from '../lib/behavior-gate.js';
+import { readCapabilityFamily } from '../lib/discovery-capabilities.js';
+const SEAM = '/v1/host/sample/voice/barge-in';
+function realtimeVoiceOf(ai: Record<string, unknown> | undefined): Record<string, unknown> | undefined {
+  const rv = (ai as { realtimeVoice?: unknown })?.realtimeVoice;
+  return rv && typeof rv === 'object' ? (rv as Record<string, unknown>) : undefined;
+}
+function eventsOf(json: unknown): Array<{ type?: string }> {
+  const e = (json as { events?: unknown })?.events;
+  return Array.isArray(e) ? (e as Array<{ type?: string }>) : [];
+}
+describe('voice-bargein-no-partial-leak (RFC 0106 §F INV-3)', () => {
+  it('barge-in cancels with no synthesis chunk emitted after voice.cancelled', async () => {
+    const ai = await readCapabilityFamily<Record<string, unknown>>('aiProviders');
+    const advertised = realtimeVoiceOf(ai)?.bargeIn === 'supported';
+    if (!behaviorGate('openwop-voice-bargein', advertised)) return;
+    const res = await driver.post(SEAM, {});
+    if (res.status === 404) return; // seam unwired — soft-skip
+    expect(res.status === 200, driver.describe('RFC 0106 §F', 'the barge-in seam MUST return 200')).toBe(true);
+    const types = eventsOf(res.json).map((e) => e.type);
+    const bargeIdx = types.indexOf('voice.barge_in');
+    const cancelIdx = types.indexOf('voice.cancelled');
+    expect(bargeIdx >= 0, driver.describe('RFC 0106 §D', 'a barge-in MUST emit voice.barge_in')).toBe(true);
+    expect(cancelIdx >= 0, driver.describe('RFC 0106 §D', 'a barge-in that cancels work MUST emit voice.cancelled')).toBe(true);
+    expect(cancelIdx > bargeIdx, driver.describe('RFC 0106 §D', 'voice.cancelled MUST follow voice.barge_in')).toBe(true);
+    // The load-bearing INV-3 assertion: nothing partial after the cancel.
+    const afterCancel = types.slice(cancelIdx + 1);
+    expect(
+      !afterCancel.includes('voice.synthesis_chunk'),
+      driver.describe('RFC 0106 §F INV-3', 'NO voice.synthesis_chunk (partial output) may be emitted AFTER voice.cancelled'),
+    ).toBe(true);
+  });
+});

package/src/scenarios/voice-interim-not-durable.test.ts ADDED Viewed

@@ -0,0 +1,59 @@
+/**
+ * Interim transcript is not durable (RFC 0106 §F INV-1) — behavioral.
+ *
+ * Backs the SECURITY invariant `voice-interim-not-durable` (reference-impl tier
+ * until a host proves it non-vacuously — graduates to protocol at the dual-witness
+ * step). Gated on `realtimeVoice.transcription === 'streaming'`. Soft-skips when
+ * unadvertised / when the host honestly rejects a live `streamRef` (§E) / on 404.
+ * Drives `POST /v1/host/sample/ai/call-transcriber`:
+ *
+ *   - a provisional `voice.transcript` (`isFinal: false`) MUST NOT appear AFTER the
+ *     terminal `voice.turn_commit`, and MUST NOT be the authoritative committed text;
+ *   - the committed `finalText` is the settled turn (acting on an interim that the
+ *     ASR later revised is the interim→final poisoning threat §F defends against).
+ *
+ * Spec references:
+ *   - https://github.com/openwop/openwop/blob/main/RFCS/0106-realtime-voice-session-profile.md (§F INV-1)
+ */
+import { describe, it, expect } from 'vitest';
+import { driver } from '../lib/driver.js';
+import { behaviorGate } from '../lib/behavior-gate.js';
+import { readCapabilityFamily } from '../lib/discovery-capabilities.js';
+const SEAM = '/v1/host/sample/ai/call-transcriber';
+function realtimeVoiceOf(ai: Record<string, unknown> | undefined): Record<string, unknown> | undefined {
+  const rv = (ai as { realtimeVoice?: unknown })?.realtimeVoice;
+  return rv && typeof rv === 'object' ? (rv as Record<string, unknown>) : undefined;
+}
+function errCode(json: unknown): string | undefined {
+  return (json as { error?: { code?: string } })?.error?.code;
+}
+function eventsOf(json: unknown): Array<{ type?: string; payload?: Record<string, unknown> }> {
+  const e = (json as { events?: unknown })?.events;
+  return Array.isArray(e) ? (e as Array<{ type?: string; payload?: Record<string, unknown> }>) : [];
+}
+describe('voice-interim-not-durable (RFC 0106 §F INV-1)', () => {
+  it('no provisional (isFinal:false) transcript is durable past voice.turn_commit', async () => {
+    const ai = await readCapabilityFamily<Record<string, unknown>>('aiProviders');
+    const advertised = realtimeVoiceOf(ai)?.transcription === 'streaming';
+    if (!behaviorGate('openwop-voice-interim-not-durable', advertised)) return;
+    const res = await driver.post(SEAM, { audio: { streamRef: 'stream:conformance/mic' }, interimResults: true });
+    if (res.status === 404) return; // seam unwired — soft-skip
+    if (errCode(res.json) === 'transcription_unsupported') return; // §E live transport / no test-seam arm — soft-skip
+    const events = eventsOf(res.json);
+    if (events.length === 0) return; // host returned only the result envelope — nothing observable to assert
+    const commitIdx = events.findIndex((e) => e.type === 'voice.turn_commit');
+    if (commitIdx < 0) return; // no commit observed — soft-skip
+    const afterCommit = events.slice(commitIdx + 1);
+    expect(
+      !afterCommit.some((e) => e.type === 'voice.transcript' && (e.payload ?? {}).isFinal === false),
+      driver.describe('RFC 0106 §F INV-1', 'a provisional (isFinal:false) transcript MUST NOT appear after voice.turn_commit'),
+    ).toBe(true);
+  });
+});

package/src/scenarios/voice-streamref-tenant-bound.test.ts ADDED Viewed

@@ -0,0 +1,59 @@
+/**
+ * streamRef is tenant + session bound (RFC 0106 §F INV-4) — behavioral.
+ *
+ * Backs the SECURITY invariant `voice-streamref-tenant-bound` (reference-impl tier
+ * until a host with LIVE `streamRef` transport proves it non-vacuously — graduates
+ * to protocol then). Gated on `realtimeVoice.transcription === 'streaming'`.
+ * Soft-skips when unadvertised / on 404 / when the host's live-stream transport is
+ * host-internal per §E (honest `transcription_unsupported` for a `streamRef`) —
+ * a stateless host without live transport cannot exhibit the cross-handle read, so
+ * there is nothing to bind. Drives `POST /v1/host/sample/ai/call-transcriber`:
+ *
+ *   - a `streamRef` is bound to exactly one tenant + session for its lifetime; no
+ *     buffered audio / interim transcript may be read via another handle, and a
+ *     never-finalizing stream is bounded by a max-uncommitted-audio budget (TDoS).
+ *
+ * Spec references:
+ *   - https://github.com/openwop/openwop/blob/main/RFCS/0106-realtime-voice-session-profile.md (§B.1, §F INV-4)
+ */
+import { describe, it, expect } from 'vitest';
+import { driver } from '../lib/driver.js';
+import { behaviorGate } from '../lib/behavior-gate.js';
+import { readCapabilityFamily } from '../lib/discovery-capabilities.js';
+const SEAM = '/v1/host/sample/ai/call-transcriber';
+function realtimeVoiceOf(ai: Record<string, unknown> | undefined): Record<string, unknown> | undefined {
+  const rv = (ai as { realtimeVoice?: unknown })?.realtimeVoice;
+  return rv && typeof rv === 'object' ? (rv as Record<string, unknown>) : undefined;
+}
+function errCode(json: unknown): string | undefined {
+  return (json as { error?: { code?: string } })?.error?.code;
+}
+describe('voice-streamref-tenant-bound (RFC 0106 §F INV-4)', () => {
+  it('a live streamRef is tenant+session bound (host-internal transport per §E soft-skips)', async () => {
+    const ai = await readCapabilityFamily<Record<string, unknown>>('aiProviders');
+    const advertised = realtimeVoiceOf(ai)?.transcription === 'streaming';
+    if (!behaviorGate('openwop-voice-streamref-tenant', advertised)) return;
+    // Probe whether the host honors a LIVE streamRef at all. If it rejects with
+    // transcription_unsupported (§E: live transport host-internal), there is no live
+    // conduit to bind cross-tenant — soft-skip (the invariant stays reference-impl
+    // until a host with live streamRef transport proves it).
+    const res = await driver.post(SEAM, { audio: { streamRef: 'stream:tenant-a/mic' } });
+    if (res.status === 404) return;
+    if (errCode(res.json) === 'transcription_unsupported') return; // §E — no live transport on this host
+    // A host that DOES accept a live streamRef must bind it: a second tenant presenting
+    // tenant-A's streamRef MUST be rejected (cross-handle read forbidden). Exercising the
+    // two-credential path requires a second principal the suite does not synthesize here;
+    // assert the minimum a single-credential probe can: the host did not silently echo
+    // another tenant's buffered audio for an unknown streamRef.
+    expect(
+      res.status !== 200 || (res.json as { finalText?: unknown })?.finalText !== undefined,
+      driver.describe('RFC 0106 §F INV-4', 'a host honoring a live streamRef MUST bind it to its tenant+session'),
+    ).toBe(true);
+  });
+});

package/src/scenarios/voice-synthesis-streaming.test.ts ADDED Viewed

@@ -0,0 +1,77 @@
+/**
+ * Streaming speech-synthesis arm (RFC 0106 §C) — behavioral.
+ *
+ * Gated on `capabilities.aiProviders.realtimeVoice.synthesis === 'streaming'`
+ * (root-first per RFC 0073). Soft-skips when unadvertised (default) / hard-fails
+ * under `OPENWOP_REQUIRE_BEHAVIOR=true`. Drives the documented host-sample seam
+ * `POST /v1/host/sample/ai/call-speech-synthesizer` with `stream: true`
+ * (soft-skips on 404 until a host wires it):
+ *
+ *   - returns 200 with the finalized RFC 0105 `audio` asset (EXACTLY ONE of
+ *     `url` / `base64`) — `stream: true` resolves the Promise at completion,
+ *     unchanged whole-file result shape;
+ *   - emits `voice.synthesis_chunk` run-events carrying METADATA ONLY
+ *     (`seq` + `mimeType`; bytes by `url`/`streamRef`, NOT inline base64 past
+ *     the host cap — the G8 event-log-bounded rule), with a terminal `final: true`.
+ *
+ * Spec references:
+ *   - https://github.com/openwop/openwop/blob/main/RFCS/0106-realtime-voice-session-profile.md (§C)
+ *   - https://github.com/openwop/openwop/blob/main/spec/v1/host-capabilities.md (§host.aiProviders)
+ */
+import { describe, it, expect } from 'vitest';
+import { driver } from '../lib/driver.js';
+import { behaviorGate } from '../lib/behavior-gate.js';
+import { readCapabilityFamily } from '../lib/discovery-capabilities.js';
+const SEAM = '/v1/host/sample/ai/call-speech-synthesizer';
+function realtimeVoiceOf(ai: Record<string, unknown> | undefined): Record<string, unknown> | undefined {
+  const rv = (ai as { realtimeVoice?: unknown })?.realtimeVoice;
+  return rv && typeof rv === 'object' ? (rv as Record<string, unknown>) : undefined;
+}
+function eventsOf(json: unknown): Array<{ type?: string; payload?: Record<string, unknown> }> {
+  const e = (json as { events?: unknown })?.events;
+  return Array.isArray(e) ? (e as Array<{ type?: string; payload?: Record<string, unknown> }>) : [];
+}
+describe('voice-synthesis-streaming (RFC 0106 §C)', () => {
+  it('stream:true resolves the finalized asset and emits metadata-only voice.synthesis_chunk events', async () => {
+    const ai = await readCapabilityFamily<Record<string, unknown>>('aiProviders');
+    const advertised = realtimeVoiceOf(ai)?.synthesis === 'streaming';
+    if (!behaviorGate('openwop-voice-synthesis', advertised)) return;
+    const res = await driver.post(SEAM, { text: 'Welcome to the weekly digest.', voiceId: 'host:narrator-test', stream: true });
+    if (res.status === 404) return; // seam unwired — soft-skip
+    expect(
+      res.status === 200,
+      driver.describe('RFC 0106 §C', 'an advertised host MUST resolve stream:true with 200'),
+    ).toBe(true);
+    const audio = (res.json as { audio?: Record<string, unknown> })?.audio;
+    expect(audio !== undefined, driver.describe('RFC 0106 §C', 'the response MUST carry the finalized `audio` asset')).toBe(true);
+    if (audio) {
+      const hasUrl = typeof audio.url === 'string' && (audio.url as string).length > 0;
+      const hasB64 = typeof audio.base64 === 'string' && (audio.base64 as string).length > 0;
+      expect(hasUrl !== hasB64, driver.describe('RFC 0106 §C', 'audio MUST carry EXACTLY ONE of url/base64')).toBe(true);
+    }
+    const chunks = eventsOf(res.json).filter((e) => e.type === 'voice.synthesis_chunk');
+    expect(chunks.length >= 1, driver.describe('RFC 0106 §C', 'MUST emit ≥1 voice.synthesis_chunk run-event')).toBe(true);
+    for (const c of chunks) {
+      const p = c.payload ?? {};
+      expect(typeof p.seq === 'number', driver.describe('RFC 0106 §C', 'each chunk carries a numeric seq')).toBe(true);
+      expect(typeof p.mimeType === 'string', driver.describe('RFC 0106 §C', 'each chunk carries a mimeType')).toBe(true);
+      // Metadata-only: bytes by reference. An inline base64 is permitted ONLY under the host cap;
+      // a chunk over the RFC 0055 256 KiB inline cap MUST be a url/streamRef reference.
+      if (typeof p.base64 === 'string') {
+        expect((p.base64 as string).length <= 262144, driver.describe('RFC 0106 §C (G8)', 'inline chunk base64 MUST stay under the 256 KiB cap; else url/streamRef')).toBe(true);
+      }
+    }
+    expect(
+      chunks.some((c) => (c.payload ?? {}).final === true),
+      driver.describe('RFC 0106 §C', 'a terminal chunk MUST carry final:true'),
+    ).toBe(true);
+  });
+});

package/src/scenarios/voice-transcription-streaming.test.ts ADDED Viewed

@@ -0,0 +1,64 @@
+/**
+ * Streaming transcription round-trip (RFC 0106 §B) — behavioral.
+ *
+ * Gated on `capabilities.aiProviders.realtimeVoice.transcription === 'streaming'`.
+ * Soft-skips when unadvertised (default) / hard-fails under
+ * `OPENWOP_REQUIRE_BEHAVIOR=true`. Drives `POST /v1/host/sample/ai/call-transcriber`
+ * (soft-skips on 404 and on `transcription_unsupported` — a host whose live-stream
+ * transport is host-internal per §E honestly rejects a `streamRef`, so the
+ * non-vacuous turn requires the deterministic test-seam arm
+ * (`OPENWOP_TEST_SEAM_ENABLED`) or a finalized media asset):
+ *
+ *   - resolves with the settled turn (`finalText`, non-empty) at `voice.turn_commit`;
+ *   - any emitted `voice.transcript` carries `contentTrust: "untrusted"` (§F);
+ *   - the turn terminates with `voice.turn_commit`.
+ *
+ * Spec references:
+ *   - https://github.com/openwop/openwop/blob/main/RFCS/0106-realtime-voice-session-profile.md (§B, §F)
+ *   - https://github.com/openwop/openwop/blob/main/spec/v1/host-capabilities.md (§host.aiProviders)
+ */
+import { describe, it, expect } from 'vitest';
+import { driver } from '../lib/driver.js';
+import { behaviorGate } from '../lib/behavior-gate.js';
+import { readCapabilityFamily } from '../lib/discovery-capabilities.js';
+const SEAM = '/v1/host/sample/ai/call-transcriber';
+function realtimeVoiceOf(ai: Record<string, unknown> | undefined): Record<string, unknown> | undefined {
+  const rv = (ai as { realtimeVoice?: unknown })?.realtimeVoice;
+  return rv && typeof rv === 'object' ? (rv as Record<string, unknown>) : undefined;
+}
+function errCode(json: unknown): string | undefined {
+  return (json as { error?: { code?: string } })?.error?.code;
+}
+function eventsOf(json: unknown): Array<{ type?: string; payload?: Record<string, unknown> }> {
+  const e = (json as { events?: unknown })?.events;
+  return Array.isArray(e) ? (e as Array<{ type?: string; payload?: Record<string, unknown> }>) : [];
+}
+describe('voice-transcription-streaming (RFC 0106 §B)', () => {
+  it('resolves a settled turn at voice.turn_commit with untrusted transcript events', async () => {
+    const ai = await readCapabilityFamily<Record<string, unknown>>('aiProviders');
+    const advertised = realtimeVoiceOf(ai)?.transcription === 'streaming';
+    if (!behaviorGate('openwop-voice-transcription', advertised)) return;
+    const res = await driver.post(SEAM, { audio: { streamRef: 'stream:conformance/mic' }, languageCode: 'en-US' });
+    if (res.status === 404) return; // seam unwired — soft-skip
+    // §E: a stateless host with no live transport honestly rejects a live streamRef.
+    if (errCode(res.json) === 'transcription_unsupported') return; // soft-skip (no live transport / no test-seam arm)
+    expect(res.status === 200, driver.describe('RFC 0106 §B', 'a produced turn MUST return 200')).toBe(true);
+    const finalText = (res.json as { finalText?: unknown })?.finalText;
+    expect(typeof finalText === 'string' && (finalText as string).length > 0, driver.describe('RFC 0106 §B', 'the turn MUST resolve a non-empty finalText at turn_commit')).toBe(true);
+    const events = eventsOf(res.json);
+    if (events.length > 0) {
+      for (const ev of events.filter((e) => e.type === 'voice.transcript')) {
+        expect((ev.payload ?? {}).contentTrust === 'untrusted', driver.describe('RFC 0106 §F INV-2', 'every voice.transcript MUST carry contentTrust:"untrusted"')).toBe(true);
+      }
+      expect(events.some((e) => e.type === 'voice.turn_commit'), driver.describe('RFC 0106 §B', 'the turn MUST terminate with voice.turn_commit')).toBe(true);
+    }
+  });
+});

package/src/scenarios/voice-transcription-unadvertised.test.ts ADDED Viewed

@@ -0,0 +1,46 @@
+/**
+ * Streaming transcription on an unadvertising host (RFC 0106 §B) — behavioral.
+ *
+ * Gated by ABSENCE: active precisely when `realtimeVoice.transcription` is NOT
+ * advertised but the seam exists. Soft-skips otherwise (default) / hard-fails
+ * under `OPENWOP_REQUIRE_BEHAVIOR=true`. A host that does NOT advertise streaming
+ * transcription MUST reject `ctx.callTranscriber` with `transcription_unsupported`
+ * (never a 200 success, never a silent no-op) — paralleling RFC 0105's
+ * `speech_synthesis_unsupported` / RFC 0091's `unsupported_modality`.
+ *
+ * Spec references:
+ *   - https://github.com/openwop/openwop/blob/main/RFCS/0106-realtime-voice-session-profile.md (§B)
+ *   - https://github.com/openwop/openwop/blob/main/spec/v1/host-capabilities.md (§host.aiProviders Failure modes)
+ */
+import { describe, it, expect } from 'vitest';
+import { driver } from '../lib/driver.js';
+import { behaviorGate } from '../lib/behavior-gate.js';
+import { readCapabilityFamily } from '../lib/discovery-capabilities.js';
+const SEAM = '/v1/host/sample/ai/call-transcriber';
+function realtimeVoiceOf(ai: Record<string, unknown> | undefined): Record<string, unknown> | undefined {
+  const rv = (ai as { realtimeVoice?: unknown })?.realtimeVoice;
+  return rv && typeof rv === 'object' ? (rv as Record<string, unknown>) : undefined;
+}
+function errCode(json: unknown): string | undefined {
+  return (json as { error?: { code?: string } })?.error?.code;
+}
+describe('voice-transcription-unadvertised (RFC 0106 §B)', () => {
+  it('a host NOT advertising realtimeVoice.transcription MUST reject with transcription_unsupported', async () => {
+    const ai = await readCapabilityFamily<Record<string, unknown>>('aiProviders');
+    const advertised = realtimeVoiceOf(ai)?.transcription === 'streaming';
+    if (!behaviorGate('openwop-voice-transcription-unadvertised', !advertised)) return;
+    const res = await driver.post(SEAM, { audio: { streamRef: 'stream:conformance/mic' } });
+    if (res.status === 404) return; // seam unwired — soft-skip
+    expect(res.status !== 200, driver.describe('RFC 0106 §B', 'an unadvertising host MUST NOT return a 200 (never a no-op)')).toBe(true);
+    expect(
+      errCode(res.json) === 'transcription_unsupported',
+      driver.describe('RFC 0106 §B', 'the call MUST be rejected with `transcription_unsupported`'),
+    ).toBe(true);
+  });
+});