@beyondwork/docx-react-component 1.0.0

package/docs/evals/cases/README.md

@@ -0,0 +1,47 @@
+---
+title: "Wave Benchmark Cases"
+summary: "Deterministic local benchmark cases for Wave-native coordination, routing, and closure evaluation."
+---
+
+# Wave Benchmark Cases
+
+Each file in this directory defines one deterministic benchmark case consumed by `wave benchmark`.
+
+## Why These Cases Exist
+
+The benchmark catalog describes *what* a benchmark is meant to measure. These case files provide the local executable fixtures that let the repo score those ideas consistently.
+
+They are designed to be:
+
+- cheap
+- deterministic
+- transparent
+- rooted in current Wave surfaces such as summaries, inboxes, request routing, and closure guards
+
+## File Shape
+
+Each case file is a single JSON object with:
+
+- `id`
+- `familyId`
+- `benchmarkId`
+- `supportedArms`
+- `fixture`
+- `expectations`
+- `scoring`
+
+## Current Arms
+
+The runner currently compares:
+
+- `single-agent`
+- `multi-agent-minimal`
+- `full-wave`
+
+The `full-wave-plus-improvement` arm is supported by the loader for later benchmark-improvement loops but is not part of the initial deterministic corpus.
+
+## Current Limitation
+
+The initial corpus is projection-backed rather than live-run-backed. It evaluates how well the current Wave substrate compiles and routes coordination state before we spend runtime budget on larger live suites.
+
+That is intentional for the first milestone. The next layer will add trace-backed and external benchmark adapters on top of this format.

package/docs/evals/cases/wave-blackboard-inbox-targeting.json

@@ -0,0 +1,73 @@
+{
+  "version": 1,
+  "id": "wave-blackboard-inbox-targeting",
+  "title": "Inbox Targeting Fidelity",
+  "summary": "Critical doc and runtime facts should survive projection into the right owner inboxes instead of staying buried in raw coordination.",
+  "familyId": "blackboard-fidelity",
+  "benchmarkId": "inbox-targeting-fidelity",
+  "kind": "projection",
+  "supportedArms": ["single-agent", "multi-agent-minimal", "full-wave"],
+  "scoring": {
+    "kind": "projection-fidelity",
+    "primaryMetric": "targeted-inbox-recall",
+    "thresholds": {
+      "targeted-inbox-recall": 100,
+      "projection-consistency-rate": 100
+    },
+    "practicalWinThreshold": 20
+  },
+  "expectations": {
+    "summaryFacts": ["docs must note the new queue retry ceiling"],
+    "targetedInboxes": {
+      "a9": ["docs must note the new queue retry ceiling"],
+      "a1": ["runtime must enforce retry ceiling 3 before enqueue"]
+    }
+  },
+  "fixture": {
+    "lane": "main",
+    "waveNumber": 0,
+    "primaryAgentId": "a1",
+    "agents": [
+      {
+        "agentId": "a1",
+        "title": "Runtime Owner",
+        "ownedPaths": ["src/queue/retries.ts"],
+        "capabilities": ["runtime"]
+      },
+      {
+        "agentId": "a9",
+        "title": "Documentation Steward",
+        "ownedPaths": ["docs/plans/current-state.md"],
+        "capabilities": ["documentation"]
+      }
+    ],
+    "records": [
+      {
+        "id": "req-runtime-retry-cap",
+        "kind": "request",
+        "lane": "main",
+        "wave": 0,
+        "agentId": "a8",
+        "targets": ["agent:a1"],
+        "status": "open",
+        "priority": "high",
+        "artifactRefs": ["src/queue/retries.ts"],
+        "summary": "runtime must enforce retry ceiling 3 before enqueue",
+        "detail": "This runtime-facing fact must stay visible to the implementation owner."
+      },
+      {
+        "id": "req-doc-retry-cap",
+        "kind": "blocker",
+        "lane": "main",
+        "wave": 0,
+        "agentId": "a8",
+        "targets": ["agent:a9"],
+        "status": "open",
+        "priority": "normal",
+        "artifactRefs": ["docs/plans/current-state.md"],
+        "summary": "docs must note the new queue retry ceiling",
+        "detail": "The documentation steward needs the same coordination fact in a docs-owned surface."
+      }
+    ]
+  }
+}

package/docs/evals/cases/wave-contradiction-conflict.json

@@ -0,0 +1,104 @@
+{
+  "version": 1,
+  "id": "wave-contradiction-conflict",
+  "title": "Claim Conflict Detection",
+  "summary": "Conflicting claims should be surfaced to the integration steward and converted into explicit repair work.",
+  "familyId": "contradiction-recovery",
+  "benchmarkId": "claim-conflict-detection",
+  "kind": "projection",
+  "supportedArms": ["single-agent", "multi-agent-minimal", "full-wave"],
+  "scoring": {
+    "kind": "contradiction-recovery",
+    "primaryMetric": "contradiction-detection-rate",
+    "thresholds": {
+      "contradiction-detection-rate": 100,
+      "repair-closure-rate": 100
+    },
+    "practicalWinThreshold": 25
+  },
+  "expectations": {
+    "targetedInboxes": {
+      "a8": [
+        "claim one: config flag enable_fast_path is safe in prod",
+        "claim two: config flag enable_fast_path leaks stale auth data"
+      ]
+    },
+    "requiredAssignments": [
+      {
+        "requestId": "repair-fast-path",
+        "assignedAgentId": "a8"
+      }
+    ]
+  },
+  "fixture": {
+    "lane": "main",
+    "waveNumber": 0,
+    "primaryAgentId": "a1",
+    "capabilityRouting": {
+      "preferredAgents": {
+        "integration": ["a8"]
+      }
+    },
+    "agents": [
+      {
+        "agentId": "a1",
+        "title": "Runtime Owner",
+        "ownedPaths": ["src/auth/fast-path.ts"],
+        "capabilities": ["runtime"]
+      },
+      {
+        "agentId": "a2",
+        "title": "Security Reviewer",
+        "ownedPaths": ["src/auth/session.ts"],
+        "capabilities": ["security"]
+      },
+      {
+        "agentId": "a8",
+        "title": "Integration Steward",
+        "ownedPaths": [".tmp/main-wave-launcher/integration/wave-0.md"],
+        "capabilities": ["integration"]
+      }
+    ],
+    "records": [
+      {
+        "id": "claim-fast-safe",
+        "kind": "claim",
+        "lane": "main",
+        "wave": 0,
+        "agentId": "a1",
+        "targets": ["agent:a8"],
+        "status": "open",
+        "priority": "high",
+        "artifactRefs": ["src/auth/fast-path.ts"],
+        "summary": "claim one: config flag enable_fast_path is safe in prod",
+        "detail": "The runtime owner believes the fast path is safe."
+      },
+      {
+        "id": "claim-fast-leak",
+        "kind": "claim",
+        "lane": "main",
+        "wave": 0,
+        "agentId": "a2",
+        "targets": ["agent:a8"],
+        "status": "open",
+        "priority": "high",
+        "artifactRefs": ["src/auth/session.ts", "src/auth/fast-path.ts"],
+        "summary": "claim two: config flag enable_fast_path leaks stale auth data",
+        "detail": "The security reviewer believes the same flag is unsafe."
+      },
+      {
+        "id": "repair-fast-path",
+        "kind": "request",
+        "lane": "main",
+        "wave": 0,
+        "agentId": "a8",
+        "targets": ["capability:integration"],
+        "status": "open",
+        "priority": "high",
+        "artifactRefs": ["src/auth/fast-path.ts"],
+        "summary": "Turn the contradiction into explicit repair work before closure",
+        "detail": "Integration must own the conflict repair loop."
+      }
+    ]
+  }
+}

package/docs/evals/cases/wave-expert-routing-preservation.json

@@ -0,0 +1,69 @@
+{
+  "version": 1,
+  "id": "wave-expert-routing-preservation",
+  "title": "Expert Routing Preservation",
+  "summary": "A capability-targeted request should route to the database specialist rather than diffuse into generic ownership.",
+  "familyId": "expertise-leverage",
+  "benchmarkId": "expert-routing-preservation",
+  "kind": "projection",
+  "supportedArms": ["single-agent", "multi-agent-minimal", "full-wave"],
+  "scoring": {
+    "kind": "expertise-routing",
+    "primaryMetric": "capability-routing-precision",
+    "thresholds": {
+      "capability-routing-precision": 100,
+      "expert-preservation-rate": 100
+    },
+    "practicalWinThreshold": 25
+  },
+  "expectations": {
+    "requiredAssignments": [
+      {
+        "requestId": "req-covering-index",
+        "assignedAgentId": "a2"
+      }
+    ],
+    "targetedInboxes": {
+      "a2": ["database expert says add a covering index on tenant_id and updated_at"]
+    }
+  },
+  "fixture": {
+    "lane": "main",
+    "waveNumber": 0,
+    "primaryAgentId": "a1",
+    "capabilityRouting": {
+      "preferredAgents": {
+        "database": ["a2"]
+      }
+    },
+    "agents": [
+      {
+        "agentId": "a1",
+        "title": "Generalist Owner",
+        "ownedPaths": ["src/reporting/service.ts"],
+        "capabilities": ["runtime"]
+      },
+      {
+        "agentId": "a2",
+        "title": "Database Specialist",
+        "ownedPaths": ["db/indexes/reporting.sql"],
+        "capabilities": ["database"]
+      }
+    ],
+    "records": [
+      {
+        "id": "req-covering-index",
+        "kind": "request",
+        "lane": "main",
+        "wave": 0,
+        "agentId": "a8",
+        "targets": ["capability:database"],
+        "status": "open",
+        "priority": "high",
+        "artifactRefs": ["db/indexes/reporting.sql"],
+        "summary": "database expert says add a covering index on tenant_id and updated_at",
+        "detail": "The database specialist should own this request rather than having it averaged away."
+      }
+    ]
+  }
+}

package/docs/evals/cases/wave-hidden-profile-private-evidence.json

@@ -0,0 +1,81 @@
+{
+  "version": 1,
+  "id": "wave-hidden-profile-private-evidence",
+  "title": "Private Evidence Integration",
+  "summary": "Critical facts are split across two specialists and only the full Wave arm should surface both through targeted inboxes.",
+  "familyId": "hidden-profile-pooling",
+  "benchmarkId": "private-evidence-integration",
+  "kind": "projection",
+  "supportedArms": ["single-agent", "multi-agent-minimal", "full-wave"],
+  "scoring": {
+    "kind": "distributed-info",
+    "primaryMetric": "distributed-info-accuracy",
+    "thresholds": {
+      "distributed-info-accuracy": 100
+    },
+    "practicalWinThreshold": 20
+  },
+  "expectations": {
+    "globalFacts": [
+      "customer-facing outage is isolated to shard blue",
+      "the rollback must preserve migration 20260321_add_backfill_guard"
+    ],
+    "targetedInboxes": {
+      "a1": ["customer-facing outage is isolated to shard blue"],
+      "a2": ["the rollback must preserve migration 20260321_add_backfill_guard"]
+    }
+  },
+  "fixture": {
+    "lane": "main",
+    "waveNumber": 0,
+    "primaryAgentId": "a1",
+    "agents": [
+      {
+        "agentId": "a1",
+        "title": "API Specialist",
+        "ownedPaths": ["src/api/server.ts"],
+        "capabilities": ["api"]
+      },
+      {
+        "agentId": "a2",
+        "title": "Migration Specialist",
+        "ownedPaths": ["db/migrations/20260321_add_backfill_guard.sql"],
+        "capabilities": ["database"]
+      },
+      {
+        "agentId": "a8",
+        "title": "Integration Steward",
+        "ownedPaths": [".tmp/main-wave-launcher/integration/wave-0.md"],
+        "capabilities": ["integration"]
+      }
+    ],
+    "records": [
+      {
+        "id": "req-blue-shard",
+        "kind": "request",
+        "lane": "main",
+        "wave": 0,
+        "agentId": "a8",
+        "targets": ["agent:a1"],
+        "status": "open",
+        "priority": "high",
+        "artifactRefs": ["src/api/server.ts"],
+        "summary": "Need API confirmation: customer-facing outage is isolated to shard blue",
+        "detail": "Integration cannot close until the API owner confirms shard blue is the only failing shard."
+      },
+      {
+        "id": "req-backfill-guard",
+        "kind": "request",
+        "lane": "main",
+        "wave": 0,
+        "agentId": "a8",
+        "targets": ["agent:a2"],
+        "status": "open",
+        "priority": "high",
+        "artifactRefs": ["db/migrations/20260321_add_backfill_guard.sql"],
+        "summary": "Need migration confirmation: the rollback must preserve migration 20260321_add_backfill_guard",
+        "detail": "The database owner holds the rollback-safe migration constraint."
+      }
+    ]
+  }
+}

package/docs/evals/cases/wave-premature-closure-guard.json

@@ -0,0 +1,71 @@
+{
+  "version": 1,
+  "id": "wave-premature-closure-guard",
+  "title": "Premature Closure Guard",
+  "summary": "A clarification-linked repair request remains open, so the full Wave arm should preserve a blocking guard instead of converging early.",
+  "familyId": "hidden-profile-pooling",
+  "benchmarkId": "premature-consensus-guard",
+  "kind": "projection",
+  "supportedArms": ["single-agent", "multi-agent-minimal", "full-wave"],
+  "scoring": {
+    "kind": "closure-guard",
+    "primaryMetric": "premature-convergence-rate",
+    "thresholds": {
+      "premature-convergence-rate": 0
+    },
+    "practicalWinThreshold": 50
+  },
+  "expectations": {
+    "clarificationRequestIds": ["clarify-missing-evidence"],
+    "requireBlockingGuard": true
+  },
+  "fixture": {
+    "lane": "main",
+    "waveNumber": 0,
+    "primaryAgentId": "a1",
+    "agents": [
+      {
+        "agentId": "a1",
+        "title": "Implementation Owner",
+        "ownedPaths": ["src/runtime.ts"],
+        "capabilities": ["runtime"]
+      },
+      {
+        "agentId": "a8",
+        "title": "Integration Steward",
+        "ownedPaths": [".tmp/main-wave-launcher/integration/wave-0.md"],
+        "capabilities": ["integration"]
+      }
+    ],
+    "records": [
+      {
+        "id": "clarify-missing-evidence",
+        "kind": "clarification-request",
+        "lane": "main",
+        "wave": 0,
+        "agentId": "a1",
+        "targets": ["launcher"],
+        "status": "open",
+        "priority": "high",
+        "artifactRefs": ["src/runtime.ts"],
+        "summary": "Missing evidence for restart durability",
+        "detail": "The implementation owner still needs proof for restart durability."
+      },
+      {
+        "id": "repair-missing-evidence",
+        "kind": "request",
+        "lane": "main",
+        "wave": 0,
+        "agentId": "a8",
+        "targets": ["agent:a1"],
+        "status": "open",
+        "priority": "high",
+        "artifactRefs": ["src/runtime.ts"],
+        "dependsOn": ["clarify-missing-evidence"],
+        "closureCondition": "clarification:clarify-missing-evidence",
+        "summary": "Repair request is still open while clarification remains unresolved",
+        "detail": "This request must remain blocking until the clarification chain is closed."
+      }
+    ]
+  }
+}

package/docs/evals/cases/wave-silo-cross-agent-state.json

@@ -0,0 +1,77 @@
+{
+  "version": 1,
+  "id": "wave-silo-cross-agent-state",
+  "title": "Cross-Agent State Reconstruction",
+  "summary": "The correct diagnosis requires facts from both the API and queue owners and should only reconstruct cleanly in the full Wave arm.",
+  "familyId": "silo-escape",
+  "benchmarkId": "cross-agent-state-reconstruction",
+  "kind": "projection",
+  "supportedArms": ["single-agent", "multi-agent-minimal", "full-wave"],
+  "scoring": {
+    "kind": "state-reconstruction",
+    "primaryMetric": "global-state-reconstruction-rate",
+    "thresholds": {
+      "global-state-reconstruction-rate": 100,
+      "summary-fact-retention-rate": 100
+    },
+    "practicalWinThreshold": 20
+  },
+  "expectations": {
+    "globalFacts": [
+      "api retries are saturating the worker queue",
+      "queue lag only spikes after the retry fanout begins"
+    ],
+    "summaryFacts": ["api retries are saturating the worker queue"],
+    "targetedInboxes": {
+      "a1": ["queue lag only spikes after the retry fanout begins"],
+      "a2": ["api retries are saturating the worker queue"]
+    }
+  },
+  "fixture": {
+    "lane": "main",
+    "waveNumber": 0,
+    "primaryAgentId": "a1",
+    "agents": [
+      {
+        "agentId": "a1",
+        "title": "API Owner",
+        "ownedPaths": ["src/api/retries.ts"],
+        "capabilities": ["api"]
+      },
+      {
+        "agentId": "a2",
+        "title": "Queue Owner",
+        "ownedPaths": ["src/queue/worker.ts"],
+        "capabilities": ["queue"]
+      }
+    ],
+    "records": [
+      {
+        "id": "block-api-fanout",
+        "kind": "blocker",
+        "lane": "main",
+        "wave": 0,
+        "agentId": "a1",
+        "targets": ["agent:a2"],
+        "status": "open",
+        "priority": "high",
+        "artifactRefs": ["src/api/retries.ts", "src/queue/worker.ts"],
+        "summary": "api retries are saturating the worker queue",
+        "detail": "The API owner sees retry fanout but needs queue evidence to reconstruct the full state."
+      },
+      {
+        "id": "block-queue-lag",
+        "kind": "blocker",
+        "lane": "main",
+        "wave": 0,
+        "agentId": "a2",
+        "targets": ["agent:a1"],
+        "status": "open",
+        "priority": "high",
+        "artifactRefs": ["src/queue/worker.ts", "src/api/retries.ts"],
+        "summary": "queue lag only spikes after the retry fanout begins",
+        "detail": "The queue owner sees the lag pattern but needs the API owner's retry context."
+      }
+    ]
+  }
+}

package/docs/evals/cases/wave-simultaneous-lockstep.json

@@ -0,0 +1,92 @@
+{
+  "version": 1,
+  "id": "wave-simultaneous-lockstep",
+  "title": "Lockstep Resolution",
+  "summary": "Two concurrent blocking requests should route to different specialists instead of collapsing into unresolved contention.",
+  "familyId": "simultaneous-coordination",
+  "benchmarkId": "lockstep-resolution",
+  "kind": "projection",
+  "supportedArms": ["single-agent", "multi-agent-minimal", "full-wave"],
+  "scoring": {
+    "kind": "simultaneous-coordination",
+    "primaryMetric": "contention-resolution-rate",
+    "thresholds": {
+      "contention-resolution-rate": 100,
+      "symmetry-breaking-rate": 100,
+      "deadlock-rate": 0
+    },
+    "practicalWinThreshold": 30
+  },
+  "expectations": {
+    "requiredAssignments": [
+      {
+        "requestId": "req-cache-guard",
+        "assignedAgentId": "a2"
+      },
+      {
+        "requestId": "req-queue-budget",
+        "assignedAgentId": "a3"
+      }
+    ],
+    "minimumDistinctAssignedAgents": 2
+  },
+  "fixture": {
+    "lane": "main",
+    "waveNumber": 0,
+    "primaryAgentId": "a1",
+    "capabilityRouting": {
+      "preferredAgents": {
+        "cache": ["a2"],
+        "queue": ["a3"]
+      }
+    },
+    "agents": [
+      {
+        "agentId": "a1",
+        "title": "Primary Owner",
+        "ownedPaths": ["src/runtime.ts"],
+        "capabilities": ["runtime"]
+      },
+      {
+        "agentId": "a2",
+        "title": "Cache Owner",
+        "ownedPaths": ["src/cache/guard.ts"],
+        "capabilities": ["cache"]
+      },
+      {
+        "agentId": "a3",
+        "title": "Queue Owner",
+        "ownedPaths": ["src/queue/budget.ts"],
+        "capabilities": ["queue"]
+      }
+    ],
+    "records": [
+      {
+        "id": "req-cache-guard",
+        "kind": "request",
+        "lane": "main",
+        "wave": 0,
+        "agentId": "a8",
+        "targets": ["capability:cache"],
+        "status": "open",
+        "priority": "high",
+        "artifactRefs": ["src/cache/guard.ts"],
+        "summary": "Concurrent fix one: cache guard must be updated before release",
+        "detail": "This blocking request should route to the cache owner."
+      },
+      {
+        "id": "req-queue-budget",
+        "kind": "request",
+        "lane": "main",
+        "wave": 0,
+        "agentId": "a8",
+        "targets": ["capability:queue"],
+        "status": "open",
+        "priority": "high",
+        "artifactRefs": ["src/queue/budget.ts"],
+        "summary": "Concurrent fix two: queue budget must be updated before release",
+        "detail": "This blocking request should route to the queue owner."
+      }
+    ]
+  }
+}