@agentskit/doc-bridge 1.7.44 → 1.9.0

package/docs/study/ab-baseline-analysis-v1.md

@@ -0,0 +1,21 @@
+# A/B baseline analysis — 2026-08-31
+
+This is the first paired baseline for `repository-only` versus `deterministic-doc-bridge`. It uses 24 anonymized task definitions, two pinned Codex CLI models, and 48 observations per arm. The result is directional and intentionally not an enterprise or causal claim.
+
+## Result
+
+The deterministic Doc Bridge arm completed 40/48 executions (83.3%) versus 38/48 (79.2%) for repository-only. Its completion p95 interval is 70.4–91.3%, while repository-only is 65.7–88.3%. Task success was 5/48 (10.4%) versus 4/47 (8.5%) where an outcome was recorded; this difference is inconclusive at this sample size.
+
+On paired observations, deterministic Doc Bridge used 5,762 fewer provider tokens on average (−2.29%, 47 pairs with token data). Its latency p95 was 3,150 ms lower (94,339 ms versus 97,489 ms). Evidence quality was higher (27.1% versus 23.4%), while evidence citation rate was slightly lower (91.7% versus 93.8%).
+
+The result is `inconclusive`: the signal is encouraging but small, one repository-only observation lacks provider token data, one repository-only observation timed out, and provider cost was not emitted. The next round must add cost attribution and independent outcome adjudication before using the study as a market claim.
+
+## Provenance
+
+- Plan: `ab-baseline-recovery-plan-v1.json`, hash `42d96e1152014318eadd2e0790259efc0ea96b138a1dcc4ac60c182ec357215f`
+- Run: `phase-8-ab-baseline-recovery-01`
+- Ledger hash: `9bf49dcee8071a4b5bfc7c515d2ee3d53c5f02344ffcf8bdeb7a412ad3f4e678`
+- Metrics report hash: `a04b7b1a3081d1011bcd99548d9929ebb96de75fd217823f498112a586533428`
+- Structured result: [ab-baseline-result-v1.json](./ab-baseline-result-v1.json)
+
+The failed first attempt remains in the immutable ledger as a failed run. The recovery result excludes it; no observation was overwritten.

package/docs/study/ab-baseline-plan-v1.json

@@ -0,0 +1,33 @@
+{
+  "type": "controlled-study-run-plan",
+  "schemaVersion": 1,
+  "planVersion": "v1-ab",
+  "protocolVersion": "v1",
+  "protocolHash": "7a56ae4da91ae56fb8b4b7e506adce525ab6fcb637d635cafb7091c2bd437adf",
+  "taskSuiteHash": "d7810828bce3c6616f00897fd7c92dfa4ecdf12e549923795cd95cc81a2b0029",
+  "sourceRevisionHash": "1dc24c4e810bfdc49d0964c21e05b425252d99528dd488010653ebd3fd41dd49",
+  "configurationHash": "c56fb5612317decb45f65a5047481663e3a9df9e23c22efde8a78e1f8b5dc544",
+  "docBridgeVersion": "1.7.45",
+  "models": [
+    { "id": "low-cost-model", "role": "low-cost", "provider": "codex", "model": "gpt-5.6-sol", "version": "codex-cli-0.149.0", "parametersHash": "6dc5481139cc4fc6960a38ffd4c7e68605108d0d3eac9ac3c269c92703200273", "contextLimit": 272000, "toolConfigurationHash": "a08b38a4fa7e559811713cabc2e2f62cb05ef266d406dcb38cf46be627417e20", "promptContractHash": "5ba19f0e4ea57c4206d2965a55fc1bbd081348a8ccf89c86ff64a81df93bf98b" },
+    { "id": "reference-model", "role": "reference", "provider": "codex", "model": "gpt-5.6-luna", "version": "codex-cli-0.149.0", "parametersHash": "785593a535c713ae8015defb031047fb9ae55926ec4ac0cb0cafcdaa5cba1e30", "contextLimit": 272000, "toolConfigurationHash": "d2fe8bbf1fa6add2b357c4a199a37224c03bbe4edf29901ff45ae0ef8ee99366", "promptContractHash": "5ba19f0e4ea57c4206d2965a55fc1bbd081348a8ccf89c86ff64a81df93bf98b" }
+  ],
+  "scenarios": [
+    { "id": "repository-only", "network": false },
+    { "id": "deterministic-doc-bridge", "network": false },
+    { "id": "registry-assisted", "agentId": "ecosystem-doc-bridge-corpus-scanner", "agentVersion": "v1.0.0", "network": false }
+  ],
+  "taskIds": [
+    "consumer-01-discovery", "consumer-01-architecture", "consumer-01-documentation", "consumer-01-implementation",
+    "consumer-02-discovery", "consumer-02-architecture", "consumer-02-documentation", "consumer-02-implementation",
+    "consumer-03-discovery", "consumer-03-architecture", "consumer-03-documentation", "consumer-03-implementation",
+    "consumer-04-discovery", "consumer-04-architecture", "consumer-04-documentation", "consumer-04-implementation",
+    "consumer-05-discovery", "consumer-05-architecture", "consumer-05-documentation", "consumer-05-implementation",
+    "consumer-06-discovery", "consumer-06-architecture", "consumer-06-documentation", "consumer-06-implementation"
+  ],
+  "sampling": { "strategy": "pairwise-task-strata", "sampleSize": 96, "scenarioIds": ["repository-only", "deterministic-doc-bridge"] },
+  "budget": { "maxTokens": 400000, "maxRuntimeMs": 180000, "maxOutputBytes": 256000, "maxAttempts": 1 },
+  "runId": "phase-8-ab-baseline-01",
+  "contentHashAlgo": "sha256-normalized-v1",
+  "contentHash": "ab735034299c9c44f464d31f2e95e637dc436416d1eb156b5e75f743b4c4ecc5"
+}

package/docs/study/ab-baseline-recovery-plan-v1.json

@@ -0,0 +1,33 @@
+{
+  "type": "controlled-study-run-plan",
+  "schemaVersion": 1,
+  "planVersion": "v1-ab-recovery",
+  "protocolVersion": "v1",
+  "protocolHash": "7a56ae4da91ae56fb8b4b7e506adce525ab6fcb637d635cafb7091c2bd437adf",
+  "taskSuiteHash": "d7810828bce3c6616f00897fd7c92dfa4ecdf12e549923795cd95cc81a2b0029",
+  "sourceRevisionHash": "1dc24c4e810bfdc49d0964c21e05b425252d99528dd488010653ebd3fd41dd49",
+  "configurationHash": "b1e6373e423f20f24e991d9c9d5f1170a1230057c11d2462311c8244ec6df3b1",
+  "docBridgeVersion": "1.7.45",
+  "models": [
+    { "id": "low-cost-model", "role": "low-cost", "provider": "codex", "model": "gpt-5.6-sol", "version": "codex-cli-0.149.0", "parametersHash": "6dc5481139cc4fc6960a38ffd4c7e68605108d0d3eac9ac3c269c92703200273", "contextLimit": 272000, "toolConfigurationHash": "a08b38a4fa7e559811713cabc2e2f62cb05ef266d406dcb38cf46be627417e20", "promptContractHash": "5ba19f0e4ea57c4206d2965a55fc1bbd081348a8ccf89c86ff64a81df93bf98b" },
+    { "id": "reference-model", "role": "reference", "provider": "codex", "model": "gpt-5.6-luna", "version": "codex-cli-0.149.0", "parametersHash": "785593a535c713ae8015defb031047fb9ae55926ec4ac0cb0cafcdaa5cba1e30", "contextLimit": 272000, "toolConfigurationHash": "d2fe8bbf1fa6add2b357c4a199a37224c03bbe4edf29901ff45ae0ef8ee99366", "promptContractHash": "5ba19f0e4ea57c4206d2965a55fc1bbd081348a8ccf89c86ff64a81df93bf98b" }
+  ],
+  "scenarios": [
+    { "id": "repository-only", "network": false },
+    { "id": "deterministic-doc-bridge", "network": false },
+    { "id": "registry-assisted", "agentId": "ecosystem-doc-bridge-corpus-scanner", "agentVersion": "v1.0.0", "network": false }
+  ],
+  "taskIds": [
+    "consumer-01-discovery", "consumer-01-architecture", "consumer-01-documentation", "consumer-01-implementation",
+    "consumer-02-discovery", "consumer-02-architecture", "consumer-02-documentation", "consumer-02-implementation",
+    "consumer-03-discovery", "consumer-03-architecture", "consumer-03-documentation", "consumer-03-implementation",
+    "consumer-04-discovery", "consumer-04-architecture", "consumer-04-documentation", "consumer-04-implementation",
+    "consumer-05-discovery", "consumer-05-architecture", "consumer-05-documentation", "consumer-05-implementation",
+    "consumer-06-discovery", "consumer-06-architecture", "consumer-06-documentation", "consumer-06-implementation"
+  ],
+  "sampling": { "strategy": "pairwise-task-strata", "sampleSize": 96, "scenarioIds": ["repository-only", "deterministic-doc-bridge"] },
+  "budget": { "maxTokens": 400000, "maxRuntimeMs": 180000, "maxOutputBytes": 256000, "maxAttempts": 1 },
+  "runId": "phase-8-ab-baseline-recovery-01",
+  "contentHashAlgo": "sha256-normalized-v1",
+  "contentHash": "42d96e1152014318eadd2e0790259efc0ea96b138a1dcc4ac60c182ec357215f"
+}

package/docs/study/ab-baseline-result-v1.json

@@ -0,0 +1,79 @@
+{
+  "type": "controlled-study-ab-result",
+  "schemaVersion": 1,
+  "resultVersion": "v1",
+  "round": "ab-baseline-2026-08-31",
+  "runId": "phase-8-ab-baseline-recovery-01",
+  "planHash": "42d96e1152014318eadd2e0790259efc0ea96b138a1dcc4ac60c182ec357215f",
+  "ledgerHash": "9bf49dcee8071a4b5bfc7c515d2ee3d53c5f02344ffcf8bdeb7a412ad3f4e678",
+  "metricsReportHash": "a04b7b1a3081d1011bcd99548d9929ebb96de75fd217823f498112a586533428",
+  "sample": {
+    "taskCount": 24,
+    "modelCount": 2,
+    "scenarioCount": 2,
+    "observationsPerArm": 48,
+    "pairedComparisons": 48
+  },
+  "arms": [
+    {
+      "scenarioId": "repository-only",
+      "observationCount": 48,
+      "executionStatus": { "completed": 38, "budget-exceeded": 9, "timed-out": 1 },
+      "completedRate": 0.7916666667,
+      "completedConfidence95": { "low": 0.6574, "high": 0.8827 },
+      "taskOutcome": { "success": 4, "partial": 29, "blocked": 12, "incomplete": 2, "missing": 1 },
+      "successRate": 0.085106383,
+      "successOutcomeCoverage": 47,
+      "evidenceCitationRate": 0.9375,
+      "evidenceQualityRate": 0.2340425532,
+      "providerTokens": 11841294,
+      "providerTokenObservations": 47,
+      "latencyP95Ms": 97489,
+      "contextBytesP95": 2085,
+      "responseBytesP95": 1084,
+      "totalCostUsd": null
+    },
+    {
+      "scenarioId": "deterministic-doc-bridge",
+      "observationCount": 48,
+      "executionStatus": { "completed": 40, "budget-exceeded": 8, "timed-out": 0 },
+      "completedRate": 0.8333333333,
+      "completedConfidence95": { "low": 0.7042, "high": 0.913 },
+      "taskOutcome": { "success": 5, "partial": 22, "blocked": 19, "incomplete": 2 },
+      "successRate": 0.1041666667,
+      "successOutcomeCoverage": 48,
+      "evidenceCitationRate": 0.9166666667,
+      "evidenceQualityRate": 0.2708333333,
+      "providerTokens": 12142335,
+      "providerTokenObservations": 48,
+      "latencyP95Ms": 94339,
+      "contextBytesP95": 2094,
+      "responseBytesP95": 1120,
+      "totalCostUsd": null
+    }
+  ],
+  "pairedDeltas": {
+    "providerTokensAverage": -5761.7021277,
+    "providerTokensRelative": -0.022868,
+    "latencyAverageMs": 609.5625,
+    "latencyP95Ms": -3150,
+    "contextP95Bytes": 9,
+    "responseP95Bytes": 22,
+    "completedRate": 0.0416666666,
+    "successRate": 0.0190602837,
+    "evidenceCitationRate": -0.0208333333,
+    "evidenceQualityRate": 0.0359297801
+  },
+  "interpretation": {
+    "classification": "inconclusive",
+    "summary": "The deterministic Doc Bridge arm shows higher completion and evidence-quality rates and lower latency p95 in this sample, but the paired token reduction is small and citation rate is slightly lower. The sample is too small and outcome coverage is incomplete for an enterprise or causal claim."
+  },
+  "limitations": [
+    "Provider cost was not emitted by the CLI adapter; cost comparison is not analyzed.",
+    "Repository-only has one observation without provider token counts and one timed-out execution; token comparison uses 47 paired token observations.",
+    "Task outcomes were not adjudicated by an independent reviewer; success rates are directional study measurements.",
+    "This is one controlled run with 24 tasks and two models; it does not establish causality or generalize to other repositories."
+  ],
+  "contentHashAlgo": "sha256-normalized-v1",
+  "contentHash": "94ac03bcb9f1d600ded42084503ca27d6a3a8e730a338b05fdd3c365d5e5ed7a"
+}

package/docs/study/documentation-audit-round-2026-08-31.json

@@ -0,0 +1,183 @@
+{
+  "type": "documentation-audit-round",
+  "schemaVersion": 1,
+  "roundId": "deterministic-doc-audit-2026-08-31",
+  "evidenceClass": "observational",
+  "observedAt": "2026-08-31T12:41:43.000Z",
+  "tool": {
+    "package": "@agentskit/doc-bridge",
+    "version": "1.7.45",
+    "pipelineVersion": "1.1.9",
+    "analyzerVersions": {
+      "repository": "1.1.1",
+      "js-ts": "1.3.4"
+    }
+  },
+  "population": [
+    {
+      "id": "consumer-01",
+      "sourceRevision": "0551139b338745da778fffaad15df2a521eca561",
+      "configurationHash": "8b01bbcbc686cb6050a8602de90d6c451131bf4aea9038f0b3a93f110bbda224",
+      "snapshotHash": "22a00a742c20fe763c376c81fe9892f16d143a76b7e079b4cf0892455720c52b",
+      "reconciliationHash": "8cbb4953b29bf096a1255e123bac9ea9167b12a01076b65fc2e646a5d54a948e",
+      "reportHash": "a1766bb82073d134fecead8fd90fcb0f275a51c4cc12bd3f93c7eebb52deeed6",
+      "status": "needs-review",
+      "metrics": {
+        "documentCount": 1506,
+        "packageCount": 25,
+        "packageCoverageRate": 1,
+        "exampleRate": 0.4296148738,
+        "exactDuplicateGroups": 0,
+        "structureGapCount": 0,
+        "contradictionCount": 0,
+        "staleCount": 0,
+        "criticalDocumentCount": 71,
+        "criticalOwnerCount": 0,
+        "criticalLifecycleCount": 0,
+        "criticalSourceOfTruthCount": 0,
+        "criticalValidationPathCount": 0,
+        "semanticFindingsNotAnalyzed": 1
+      }
+    },
+    {
+      "id": "consumer-02",
+      "sourceRevision": "29f1ca1eff0b3f8bbad11a3616828a1a3d45623e458a50113c44a5e1db44e96f",
+      "configurationHash": "70aba95ef37af3f3ba7b9dbcfaad1d4dc12b4a9f26921e401cd3719462831f62",
+      "snapshotHash": "7213faf33b0e2cdee8fe846b1dfb0d02220524aaa1ac2efa81f45bb0309a198f",
+      "reconciliationHash": "92be573e4b4119717e1feb5282ba25c37f958223ac1f9a185a8424eb6810b263",
+      "reportHash": "a286f125b075889ee54168ccb3abd6a34854cb603fd3cfa54463f02c4dfd9d74",
+      "status": "needs-review",
+      "metrics": {
+        "documentCount": 165,
+        "packageCount": 20,
+        "packageCoverageRate": 1,
+        "exampleRate": 0.6181818182,
+        "exactDuplicateGroups": 0,
+        "structureGapCount": 0,
+        "contradictionCount": 0,
+        "staleCount": 0,
+        "criticalDocumentCount": 28,
+        "criticalOwnerCount": 0,
+        "criticalLifecycleCount": 0,
+        "criticalSourceOfTruthCount": 0,
+        "criticalValidationPathCount": 0,
+        "semanticFindingsNotAnalyzed": 1
+      }
+    },
+    {
+      "id": "consumer-03",
+      "sourceRevision": "e34b7a0d60f870856942319b323a1dcc942d2e8511914a4cfe74b83c962101cb",
+      "configurationHash": "d3d863d650a980bcc32b290af594b39988fdeba78ca1cb39f70c6020bb94f6d3",
+      "snapshotHash": "cf060e2a910dc0b12e6b0a538260e2f9ea5f404c664dd97897509f7172d7ef9a",
+      "reconciliationHash": "fa25789f81194f71cd8bd7cf4f5be8b0445bf789d3530ea0a54e00b2acbee1ef",
+      "reportHash": "e0f32b9d606604b680161d33abe40f3cd9b7a1461db240c75eae8eb180bcd971",
+      "status": "needs-review",
+      "metrics": {
+        "documentCount": 1348,
+        "packageCount": 82,
+        "packageCoverageRate": 1,
+        "exampleRate": 0.4072700297,
+        "exactDuplicateGroups": 0,
+        "structureGapCount": 0,
+        "contradictionCount": 0,
+        "staleCount": 0,
+        "criticalDocumentCount": 249,
+        "criticalOwnerCount": 0,
+        "criticalLifecycleCount": 0,
+        "criticalSourceOfTruthCount": 0,
+        "criticalValidationPathCount": 0,
+        "semanticFindingsNotAnalyzed": 1
+      }
+    },
+    {
+      "id": "consumer-04",
+      "sourceRevision": "30c864e347970f6d56d8ca9a6c9c12199e5af619f2d81a915614206d5f798cf4",
+      "configurationHash": "ad3be4f59dafc63cd9740d1cc95c2411f72c09a41a2141a150970cf93640fb36",
+      "snapshotHash": "655e90ec96c770d79e5bcee4499fced0823ffde07019a874a6b792bc31c41505",
+      "reconciliationHash": "5f8d85116f81d7698d30ea2fc6d33288dc7b1be0dddf20f51075e0a3cda5a21c",
+      "reportHash": "480718d5ab555ee2260c09eba423580fa318eeb1740d489cd0f805473d49f90c",
+      "status": "needs-review",
+      "metrics": {
+        "documentCount": 384,
+        "packageCount": 0,
+        "packageCoverageRate": null,
+        "exampleRate": 0.1614583333,
+        "exactDuplicateGroups": 0,
+        "structureGapCount": 0,
+        "contradictionCount": 0,
+        "staleCount": 0,
+        "criticalDocumentCount": 28,
+        "criticalOwnerCount": 0,
+        "criticalLifecycleCount": 0,
+        "criticalSourceOfTruthCount": 0,
+        "criticalValidationPathCount": 0,
+        "semanticFindingsNotAnalyzed": 1
+      }
+    },
+    {
+      "id": "consumer-05",
+      "sourceRevision": "e6079d4ea8f730012ddb406f14f597112f5dcf5e",
+      "configurationHash": "d16e4ece3da2d0bf8be1ea898572d697c80ae6ac84ece1f151f017f6ef347cc2",
+      "snapshotHash": "c57bb3af76a3d5ef38f79ecd1dd1de1b8f523ecd7fa7c876a3fdad9b53eb0e90",
+      "reconciliationHash": "72a3ac55d5d7d2931b60e9a179cb10903fe88cfc8fbf5ee50b1c36e7d8f7b9e8",
+      "reportHash": "b7ee459d0bf7564e170e0696cb39e245f7e1887ec1a2b3ab4115ce079daea095",
+      "status": "needs-review",
+      "metrics": {
+        "documentCount": 172,
+        "packageCount": 2,
+        "packageCoverageRate": 1,
+        "exampleRate": 0.5697674419,
+        "exactDuplicateGroups": 0,
+        "structureGapCount": 0,
+        "contradictionCount": 0,
+        "staleCount": 0,
+        "criticalDocumentCount": 28,
+        "criticalOwnerCount": 0,
+        "criticalLifecycleCount": 0,
+        "criticalSourceOfTruthCount": 0,
+        "criticalValidationPathCount": 0,
+        "semanticFindingsNotAnalyzed": 1
+      }
+    },
+    {
+      "id": "consumer-06",
+      "sourceRevision": "80f33b09c495a4a5ede0795058c67e9993cfe8efe59605e436cc11f59a3ef3bd",
+      "configurationHash": "f94d74f17dfcd00f3bcd8b972caf48371158d29244afb2e5358613736429650a",
+      "snapshotHash": "b3ec0e5b8711098e381bf6020d02a63f2e0a8385f995633914b18a066d9d1cb5",
+      "reconciliationHash": "21a54d9304711a1e9505a8f9b5b65f393dc6bb1115cff47b7432d646c1073104",
+      "reportHash": "54d6e339b43636eb9b8f6b6a49f5462750fc00f07f8e6c7aab8cdf6cf6b337c4",
+      "status": "needs-review",
+      "metrics": {
+        "documentCount": 85,
+        "packageCount": 0,
+        "packageCoverageRate": null,
+        "exampleRate": 0.5764705882,
+        "exactDuplicateGroups": 0,
+        "structureGapCount": 0,
+        "contradictionCount": 0,
+        "staleCount": 0,
+        "criticalDocumentCount": 18,
+        "criticalOwnerCount": 1,
+        "criticalLifecycleCount": 0,
+        "criticalSourceOfTruthCount": 0,
+        "criticalValidationPathCount": 0,
+        "semanticFindingsNotAnalyzed": 1
+      }
+    }
+  ],
+  "commonDimensionStatus": {
+    "correctness": "not-analyzed",
+    "completeness": "partial",
+    "clarity": "partial",
+    "agentEfficiency": "partial-or-not-analyzed",
+    "maintainability": "partial"
+  },
+  "limitations": [
+    "This is a deterministic observational snapshot, not a controlled model comparison.",
+    "Natural-language correctness, document contradictions, unnecessary content, and semantic freshness remain not-analyzed.",
+    "The snapshot records findings and hashes only; it does not contain repository names, paths, document contents, prompts, credentials, or raw agent responses.",
+    "Provider tokens, task success, latency-to-answer, rework, and human adjudication were not collected in this round."
+  ],
+  "contentHash": "bd77d126783fe1d493b240254c5bb3b86c7485d89b0eaa00299a6501993f3587",
+  "contentHashAlgo": "sha256-normalized-v1"
+}

package/docs/study/historical-evidence-v1.json

@@ -0,0 +1,252 @@
+{
+  "type": "historical-evidence-registry",
+  "schemaVersion": 1,
+  "registryVersion": "v1",
+  "records": [
+    {
+      "id": "dogfood-round-01",
+      "evidenceClass": "historical",
+      "observedAt": "2026-07-09T00:00:00.000Z",
+      "subject": { "kind": "aggregate", "id": "ecosystem-aggregate" },
+      "source": { "kind": "study-artifact", "reference": "dogfood-v1" },
+      "docBridgeVersion": "1.0.0",
+      "status": "partially-validated",
+      "metrics": { "knowledge-documents": 358, "agent-handoffs": 233, "gate-pass-rate": 1, "agent-search-hit-rate": 1 },
+      "missingMetrics": [
+        { "metricId": "tokens-to-answer", "status": "not-analyzed", "reason": "Not collected in this round." },
+        { "metricId": "documentation-correctness", "status": "not-analyzed", "reason": "Semantic review was not part of this round." },
+        { "metricId": "time-to-answer", "status": "not-analyzed", "reason": "Not collected in this round." }
+      ],
+      "limitations": ["Historical evidence is observational and not causal.", "The original task suite was not fixed."]
+    },
+    {
+      "id": "dogfood-round-02",
+      "evidenceClass": "historical",
+      "observedAt": "2026-07-09T00:00:00.000Z",
+      "subject": { "kind": "aggregate", "id": "ecosystem-aggregate" },
+      "source": { "kind": "study-artifact", "reference": "dogfood-round-2" },
+      "docBridgeVersion": "0.1.0-alpha.2",
+      "status": "partially-validated",
+      "metrics": { "knowledge-documents": 358, "agent-handoffs": 233, "agent-search-hit-rate": 1 },
+      "missingMetrics": [
+        { "metricId": "tokens-to-answer", "status": "not-analyzed", "reason": "Not collected in this round." },
+        { "metricId": "documentation-correctness", "status": "not-analyzed", "reason": "Semantic review was not part of this round." },
+        { "metricId": "study-cost", "status": "not-analyzed", "reason": "Cost accounting was not collected in this round." }
+      ],
+      "limitations": ["Historical evidence is observational and not causal.", "The original task suite was not fixed."]
+    },
+    {
+      "id": "dogfood-round-03",
+      "evidenceClass": "historical",
+      "observedAt": "2026-07-09T00:00:00.000Z",
+      "subject": { "kind": "aggregate", "id": "ecosystem-aggregate" },
+      "source": { "kind": "study-artifact", "reference": "dogfood-round-3" },
+      "docBridgeVersion": "0.1.0-alpha.3",
+      "status": "partially-validated",
+      "metrics": { "knowledge-documents": 358, "agent-handoffs": 233, "agent-search-hit-rate": 1, "ranking-validations": 4 },
+      "missingMetrics": [
+        { "metricId": "tokens-to-answer", "status": "not-analyzed", "reason": "Not collected in this round." },
+        { "metricId": "documentation-correctness", "status": "not-analyzed", "reason": "Semantic review was not part of this round." },
+        { "metricId": "study-cost", "status": "not-analyzed", "reason": "Cost accounting was not collected in this round." }
+      ],
+      "limitations": ["Historical evidence is observational and not causal.", "The original task suite was not fixed."]
+    },
+    {
+      "id": "documentation-audit-consumer-01",
+      "evidenceClass": "historical",
+      "observedAt": "2026-08-29T00:00:00.000Z",
+      "subject": { "kind": "consumer", "id": "consumer-01" },
+      "source": { "kind": "validation-plan", "reference": "documentation-audit-baseline" },
+      "status": "partially-validated",
+      "metrics": { "documents": 4098, "package-coverage": 0.988, "title-rate": 0.324, "example-rate": 0.15, "exact-duplicate-groups": 23, "structure-gaps": 2712, "contradictions": 0, "stale-documents": 0 },
+      "missingMetrics": [
+        { "metricId": "documentation-correctness", "status": "not-analyzed", "reason": "Natural-language semantic review was not deterministic in this round." },
+        { "metricId": "documentation-clarity", "status": "not-analyzed", "reason": "Human clarity review was not collected in this round." },
+        { "metricId": "tokens-to-answer", "status": "not-analyzed", "reason": "Agent task measurement was not collected in this round." }
+      ],
+      "limitations": ["This is a deterministic audit baseline, not a complete semantic quality score."]
+    },
+    {
+      "id": "documentation-audit-consumer-02",
+      "evidenceClass": "historical",
+      "observedAt": "2026-08-29T00:00:00.000Z",
+      "subject": { "kind": "consumer", "id": "consumer-02" },
+      "source": { "kind": "validation-plan", "reference": "documentation-audit-baseline" },
+      "status": "partially-validated",
+      "metrics": { "documents": 1537, "package-coverage": 1, "title-rate": 0.712, "example-rate": 0.42, "exact-duplicate-groups": 2, "structure-gaps": 0, "contradictions": 0, "stale-documents": 0 },
+      "missingMetrics": [
+        { "metricId": "documentation-correctness", "status": "not-analyzed", "reason": "Natural-language semantic review was not deterministic in this round." },
+        { "metricId": "documentation-clarity", "status": "not-analyzed", "reason": "Human clarity review was not collected in this round." },
+        { "metricId": "tokens-to-answer", "status": "not-analyzed", "reason": "Agent task measurement was not collected in this round." }
+      ],
+      "limitations": ["This is a deterministic audit baseline, not a complete semantic quality score."]
+    },
+    {
+      "id": "documentation-audit-consumer-03",
+      "evidenceClass": "historical",
+      "observedAt": "2026-08-29T00:00:00.000Z",
+      "subject": { "kind": "consumer", "id": "consumer-03" },
+      "source": { "kind": "validation-plan", "reference": "documentation-audit-baseline" },
+      "status": "partially-validated",
+      "metrics": { "documents": 169, "package-coverage": 0.952, "title-rate": 0.964, "example-rate": 0.598, "exact-duplicate-groups": 0, "structure-gaps": 1083, "contradictions": 0, "stale-documents": 0 },
+      "missingMetrics": [
+        { "metricId": "documentation-correctness", "status": "not-analyzed", "reason": "Natural-language semantic review was not deterministic in this round." },
+        { "metricId": "documentation-clarity", "status": "not-analyzed", "reason": "Human clarity review was not collected in this round." },
+        { "metricId": "tokens-to-answer", "status": "not-analyzed", "reason": "Agent task measurement was not collected in this round." }
+      ],
+      "limitations": ["This is a deterministic audit baseline, not a complete semantic quality score."]
+    },
+    {
+      "id": "documentation-audit-consumer-04",
+      "evidenceClass": "historical",
+      "observedAt": "2026-08-29T00:00:00.000Z",
+      "subject": { "kind": "consumer", "id": "consumer-04" },
+      "source": { "kind": "validation-plan", "reference": "documentation-audit-baseline" },
+      "status": "partially-validated",
+      "metrics": { "documents": 163, "package-coverage": 0, "title-rate": 0.982, "example-rate": 0.583, "exact-duplicate-groups": 0, "structure-gaps": 512, "contradictions": 0, "stale-documents": 0 },
+      "missingMetrics": [
+        { "metricId": "documentation-correctness", "status": "not-analyzed", "reason": "Natural-language semantic review was not deterministic in this round." },
+        { "metricId": "documentation-clarity", "status": "not-analyzed", "reason": "Human clarity review was not collected in this round." },
+        { "metricId": "tokens-to-answer", "status": "not-analyzed", "reason": "Agent task measurement was not collected in this round." }
+      ],
+      "limitations": ["This is a deterministic audit baseline, not a complete semantic quality score."]
+    },
+    {
+      "id": "documentation-audit-consumer-05",
+      "evidenceClass": "historical",
+      "observedAt": "2026-08-29T00:00:00.000Z",
+      "subject": { "kind": "consumer", "id": "consumer-05" },
+      "source": { "kind": "validation-plan", "reference": "documentation-audit-baseline" },
+      "status": "partially-validated",
+      "metrics": { "documents": 416, "package-coverage": 0, "title-rate": 0.998, "example-rate": 0.236, "exact-duplicate-groups": 0, "structure-gaps": 5118, "contradictions": 0, "stale-documents": 0 },
+      "missingMetrics": [
+        { "metricId": "documentation-correctness", "status": "not-analyzed", "reason": "Natural-language semantic review was not deterministic in this round." },
+        { "metricId": "documentation-clarity", "status": "not-analyzed", "reason": "Human clarity review was not collected in this round." },
+        { "metricId": "tokens-to-answer", "status": "not-analyzed", "reason": "Agent task measurement was not collected in this round." }
+      ],
+      "limitations": ["This is a deterministic audit baseline, not a complete semantic quality score."]
+    },
+    {
+      "id": "validation-cycle-02",
+      "evidenceClass": "historical",
+      "observedAt": "2026-08-27T00:00:00.000Z",
+      "subject": { "kind": "consumer", "id": "consumer-06" },
+      "source": { "kind": "validation-plan", "reference": "validation-cycle-02" },
+      "docBridgeVersion": "1.7.20",
+      "workflowRunId": "1787934948972-14360",
+      "verificationRunId": "1787935063723-14641",
+      "status": "partially-validated",
+      "metrics": { "pipeline-total-ms": 6052, "report-artifact-bytes": 26338177, "report-first-render-p95-ms": 113, "report-application-response-p95-ms": 92, "report-gesture-p95-ms": 76, "agent-search-hit-rate": 1, "agent-estimated-p95-tokens": 1067, "context-reduction": 0.99, "reconciliation-evidence-ratio": 1 },
+      "missingMetrics": [
+        { "metricId": "tokens-to-answer", "status": "not-analyzed", "reason": "Only agent context estimates were collected." },
+        { "metricId": "documentation-correctness", "status": "not-analyzed", "reason": "Semantic documentation review was outside this cycle." },
+        { "metricId": "documentation-clarity", "status": "not-analyzed", "reason": "Human clarity review was outside this cycle." },
+        { "metricId": "time-to-answer", "status": "not-analyzed", "reason": "Task answer timing was not collected." },
+        { "metricId": "study-cost", "status": "not-analyzed", "reason": "Study cost accounting was not collected." }
+      ],
+      "limitations": ["Automated report checks passed, but human visual approval remained pending.", "The consumer result is a real-world baseline, not a semantic truth set."]
+    },
+    {
+      "id": "validation-cycle-03",
+      "evidenceClass": "historical",
+      "observedAt": "2026-08-27T00:00:00.000Z",
+      "subject": { "kind": "consumer", "id": "consumer-06" },
+      "source": { "kind": "validation-plan", "reference": "validation-cycle-03" },
+      "docBridgeVersion": "1.7.21",
+      "workflowRunId": "1787937333636-16849",
+      "verificationRunId": "1787937404198-17113",
+      "status": "partially-validated",
+      "metrics": { "literal-dynamic-import-relations": 379, "unresolved-dynamic-files": 56, "runtime-wiring-candidates": 46, "report-first-render-p95-ms": 59, "report-application-response-p95-ms": 79, "report-gesture-p95-ms": 76, "agent-search-hit-rate": 1, "agent-estimated-p95-tokens": 1067, "context-reduction": 0.99 },
+      "missingMetrics": [
+        { "metricId": "tokens-to-answer", "status": "not-analyzed", "reason": "Only agent context estimates were collected." },
+        { "metricId": "documentation-correctness", "status": "not-analyzed", "reason": "Semantic documentation review was outside this cycle." },
+        { "metricId": "documentation-clarity", "status": "not-analyzed", "reason": "Human clarity review was outside this cycle." },
+        { "metricId": "time-to-answer", "status": "not-analyzed", "reason": "Task answer timing was not collected." },
+        { "metricId": "study-cost", "status": "not-analyzed", "reason": "Study cost accounting was not collected." }
+      ],
+      "limitations": ["Automated report checks passed, but human visual approval remained pending.", "Non-literal loading and runtime wiring remained explicit limitations."]
+    },
+    {
+      "id": "validation-cycle-04",
+      "evidenceClass": "historical",
+      "observedAt": "2026-08-28T00:00:00.000Z",
+      "subject": { "kind": "consumer", "id": "consumer-06" },
+      "source": { "kind": "validation-plan", "reference": "validation-cycle-04" },
+      "docBridgeVersion": "1.7.24",
+      "workflowRunId": "1787938291045-21432",
+      "verificationRunId": "1787938325493-21506",
+      "status": "partially-validated",
+      "metrics": { "pipeline-total-ms": 6094, "report-artifact-bytes": 26441496, "report-first-render-p95-ms": 110, "report-application-response-p95-ms": 71, "report-gesture-p95-ms": 76, "runtime-wiring-candidates": 116, "agent-search-hit-rate": 1, "agent-estimated-p95-tokens": 1067, "context-reduction": 0.99 },
+      "missingMetrics": [
+        { "metricId": "tokens-to-answer", "status": "not-analyzed", "reason": "Only agent context estimates were collected." },
+        { "metricId": "documentation-correctness", "status": "not-analyzed", "reason": "Semantic documentation review was outside this cycle." },
+        { "metricId": "documentation-clarity", "status": "not-analyzed", "reason": "Human clarity review was outside this cycle." },
+        { "metricId": "time-to-answer", "status": "not-analyzed", "reason": "Task answer timing was not collected." },
+        { "metricId": "study-cost", "status": "not-analyzed", "reason": "Study cost accounting was not collected." }
+      ],
+      "limitations": ["Automated report checks passed, but human visual approval remained pending.", "Runtime wiring remained conservative and partially unresolved."]
+    },
+    {
+      "id": "validation-cycle-05",
+      "evidenceClass": "historical",
+      "observedAt": "2026-08-28T00:00:00.000Z",
+      "subject": { "kind": "consumer", "id": "consumer-06" },
+      "source": { "kind": "validation-plan", "reference": "validation-cycle-05" },
+      "docBridgeVersion": "1.7.25",
+      "workflowRunId": "1787938899030-22694",
+      "verificationRunId": "1787938967570-22837",
+      "status": "partially-validated",
+      "metrics": { "pipeline-total-ms": 6042, "report-artifact-bytes": 26422816, "report-first-render-p95-ms": 58, "report-application-response-p95-ms": 71, "report-gesture-p95-ms": 75, "runtime-wiring-candidates": 54, "agent-search-hit-rate": 1, "agent-estimated-p95-tokens": 1067, "context-reduction": 0.99 },
+      "missingMetrics": [
+        { "metricId": "tokens-to-answer", "status": "not-analyzed", "reason": "Only agent context estimates were collected." },
+        { "metricId": "documentation-correctness", "status": "not-analyzed", "reason": "Semantic documentation review was outside this cycle." },
+        { "metricId": "documentation-clarity", "status": "not-analyzed", "reason": "Human clarity review was outside this cycle." },
+        { "metricId": "time-to-answer", "status": "not-analyzed", "reason": "Task answer timing was not collected." },
+        { "metricId": "study-cost", "status": "not-analyzed", "reason": "Study cost accounting was not collected." }
+      ],
+      "limitations": ["Automated report checks passed, but human visual approval remained pending.", "Runtime wiring remained conservative and partially unresolved."]
+    },
+    {
+      "id": "validation-cycle-06",
+      "evidenceClass": "historical",
+      "observedAt": "2026-08-28T00:00:00.000Z",
+      "subject": { "kind": "consumer", "id": "consumer-06" },
+      "source": { "kind": "validation-plan", "reference": "validation-cycle-06" },
+      "docBridgeVersion": "1.7.26",
+      "workflowRunId": "1787939273593-23788",
+      "verificationRunId": "1787939317943-23884",
+      "status": "partially-validated",
+      "metrics": { "pipeline-total-ms": 5903, "report-artifact-bytes": 26412971, "report-first-render-p95-ms": 106, "report-application-response-p95-ms": 71, "report-gesture-p95-ms": 77, "runtime-wiring-candidates": 22, "agent-search-hit-rate": 1, "agent-estimated-p95-tokens": 1067, "context-reduction": 0.99 },
+      "missingMetrics": [
+        { "metricId": "tokens-to-answer", "status": "not-analyzed", "reason": "Only agent context estimates were collected." },
+        { "metricId": "documentation-correctness", "status": "not-analyzed", "reason": "Semantic documentation review was outside this cycle." },
+        { "metricId": "documentation-clarity", "status": "not-analyzed", "reason": "Human clarity review was outside this cycle." },
+        { "metricId": "time-to-answer", "status": "not-analyzed", "reason": "Task answer timing was not collected." },
+        { "metricId": "study-cost", "status": "not-analyzed", "reason": "Study cost accounting was not collected." }
+      ],
+      "limitations": ["Automated report checks passed, but human visual approval remained pending.", "Runtime wiring remained conservative and partially unresolved."]
+    },
+    {
+      "id": "validation-cycle-07",
+      "evidenceClass": "historical",
+      "observedAt": "2026-08-29T00:00:00.000Z",
+      "subject": { "kind": "consumer", "id": "consumer-06" },
+      "source": { "kind": "validation-plan", "reference": "validation-cycle-07" },
+      "docBridgeVersion": "1.7.28",
+      "workflowRunId": "1787940069560-26699",
+      "verificationRunId": "1787940112369-26783",
+      "status": "partially-validated",
+      "metrics": { "pipeline-total-ms": 5910, "report-artifact-bytes": 26370691, "report-first-render-p95-ms": 113, "report-application-response-p95-ms": 71, "report-gesture-p95-ms": 78, "overview-chunk-bytes": 843002, "runtime-wiring-candidates": 9, "agent-search-hit-rate": 1, "agent-estimated-p95-tokens": 1067, "context-reduction": 0.99, "reconciliation-evidence-ratio": 1 },
+      "missingMetrics": [
+        { "metricId": "tokens-to-answer", "status": "not-analyzed", "reason": "Only agent context estimates were collected." },
+        { "metricId": "documentation-correctness", "status": "not-analyzed", "reason": "Semantic documentation review was outside this cycle." },
+        { "metricId": "documentation-clarity", "status": "not-analyzed", "reason": "Human clarity review was outside this cycle." },
+        { "metricId": "time-to-answer", "status": "not-analyzed", "reason": "Task answer timing was not collected." },
+        { "metricId": "study-cost", "status": "not-analyzed", "reason": "Study cost accounting was not collected." }
+      ],
+      "limitations": ["Automated report checks passed, but human visual approval remained pending.", "The consumer result is a real-world baseline, not a semantic truth set."]
+    }
+  ],
+  "contentHashAlgo": "sha256-normalized-v1",
+  "contentHash": "022f12245e75a16e386d20739e130d675d7aacfec0f14f3bbadd0248659ffcb0"
+}