Merge pull request #148 from aicodingstack/agent/data-integrity-backfill

feat(data): strengthen catalog integrity

Author: ericyangpan

data/changelogs.json

@@ -1,6 +1,88 @@
 {
   "version": 1,
   "entries": [
+    {
+      "id": "2026-07-19-data-integrity",
+      "date": "2026-07-19",
+      "summary": "Fixed product relationships and expanded official-source provenance for coding assistants",
+      "changes": [
+        {
+          "category": "clis",
+          "id": "claude-code-cli",
+          "change": "updated",
+          "fields": [
+            "docsUrl",
+            "latestVersion",
+            "resourceUrls",
+            "confidence",
+            "lastVerifiedAt",
+            "sources",
+            "verifiedBy"
+          ]
+        },
+        {
+          "category": "extensions",
+          "id": "claude-code",
+          "change": "updated",
+          "fields": [
+            "docsUrl",
+            "latestVersion",
+            "resourceUrls",
+            "confidence",
+            "lastVerifiedAt",
+            "sources",
+            "verifiedBy"
+          ]
+        },
+        {
+          "category": "extensions",
+          "id": "droid",
+          "change": "updated",
+          "fields": ["relatedProducts"]
+        },
+        {
+          "category": "extensions",
+          "id": "gemini-code-assist",
+          "change": "updated",
+          "fields": [
+            "docsUrl",
+            "latestVersion",
+            "license",
+            "pricing",
+            "resourceUrls",
+            "supportedIdes",
+            "confidence",
+            "lastVerifiedAt",
+            "sources",
+            "verifiedBy"
+          ]
+        },
+        {
+          "category": "extensions",
+          "id": "qoder",
+          "change": "updated",
+          "fields": ["relatedProducts"]
+        },
+        {
+          "category": "ides",
+          "id": "intellij-idea",
+          "change": "updated",
+          "fields": ["relatedProducts"]
+        },
+        {
+          "category": "ides",
+          "id": "vscode",
+          "change": "updated",
+          "fields": ["relatedProducts"]
+        },
+        {
+          "category": "ides",
+          "id": "zed",
+          "change": "updated",
+          "fields": ["relatedProducts"]
+        }
+      ]
+    },
     {
       "id": "2026-07-18-project-review",
       "date": "2026-07-18",

data/data-health.json

@@ -1,5 +1,5 @@
 {
-  "asOf": "2026-07-18",
+  "asOf": "2026-07-19",
   "thresholds": {
     "models": 30,
     "providers": 30,
@@ -10,18 +10,18 @@
   },
   "summary": {
     "totalRecords": 134,
-    "recordsWithSources": 6,
+    "recordsWithSources": 9,
     "verifiedRecords": 39,
-    "provenanceComplete": 6,
+    "provenanceComplete": 9,
     "staleVerifiedRecords": 0,
     "translationPlaceholderValues": 1411,
-    "danglingRelationships": 5,
+    "danglingRelationships": 0,
     "modelBenchmarkCoverage": 28.1,
     "productsWithPricing": 48,
     "productRecords": 48,
     "errors": 0,
-    "warnings": 38,
-    "info": 128
+    "warnings": 30,
+    "info": 125
   },
   "byCategory": {
     "ides": {
@@ -33,13 +33,13 @@
     "clis": {
       "total": 20,
       "verified": 2,
-      "provenanceComplete": 0,
+      "provenanceComplete": 1,
       "stale": 0
     },
     "extensions": {
       "total": 15,
       "verified": 3,
-      "provenanceComplete": 0,
+      "provenanceComplete": 2,
       "stale": 0
     },
     "models": {
@@ -119,69 +119,13 @@
     }
   },
   "issues": [
-    {
-      "severity": "warning",
-      "code": "dangling-related-product",
-      "category": "extensions",
-      "id": "droid",
-      "message": "References missing clis/factory."
-    },
-    {
-      "severity": "warning",
-      "code": "dangling-related-product",
-      "category": "extensions",
-      "id": "qoder",
-      "message": "References missing ides/qoder-ide."
-    },
-    {
-      "severity": "warning",
-      "code": "dangling-related-product",
-      "category": "ides",
-      "id": "intellij-idea",
-      "message": "References missing clis/idea."
-    },
-    {
-      "severity": "warning",
-      "code": "dangling-related-product",
-      "category": "ides",
-      "id": "vscode",
-      "message": "References missing clis/code."
-    },
-    {
-      "severity": "warning",
-      "code": "dangling-related-product",
-      "category": "ides",
-      "id": "zed",
-      "message": "References missing clis/zed."
-    },
-    {
-      "severity": "warning",
-      "code": "verified-without-provenance",
-      "category": "clis",
-      "id": "claude-code-cli",
-      "message": "Verified record is missing sources, review date, reviewer, or confidence."
-    },
     {
       "severity": "warning",
       "code": "verified-without-provenance",
       "category": "clis",
       "id": "kilo-code-cli",
       "message": "Verified record is missing sources, review date, reviewer, or confidence."
     },
-    {
-      "severity": "warning",
-      "code": "verified-without-provenance",
-      "category": "extensions",
-      "id": "claude-code",
-      "message": "Verified record is missing sources, review date, reviewer, or confidence."
-    },
-    {
-      "severity": "warning",
-      "code": "verified-without-provenance",
-      "category": "extensions",
-      "id": "gemini-code-assist",
-      "message": "Verified record is missing sources, review date, reviewer, or confidence."
-    },
     {
       "severity": "warning",
       "code": "verified-without-provenance",
@@ -406,13 +350,6 @@
       "id": "augment-code-cli",
       "message": "No structured source references are recorded."
     },
-    {
-      "severity": "info",
-      "code": "missing-sources",
-      "category": "clis",
-      "id": "claude-code-cli",
-      "message": "No structured source references are recorded."
-    },
     {
       "severity": "info",
       "code": "missing-sources",
@@ -539,13 +476,6 @@
       "id": "augment-code",
       "message": "No structured source references are recorded."
     },
-    {
-      "severity": "info",
-      "code": "missing-sources",
-      "category": "extensions",
-      "id": "claude-code",
-      "message": "No structured source references are recorded."
-    },
     {
       "severity": "info",
       "code": "missing-sources",
@@ -574,13 +504,6 @@
       "id": "droid",
       "message": "No structured source references are recorded."
     },
-    {
-      "severity": "info",
-      "code": "missing-sources",
-      "category": "extensions",
-      "id": "gemini-code-assist",
-      "message": "No structured source references are recorded."
-    },
     {
       "severity": "info",
       "code": "missing-sources",

docs/DATA-HEALTH.md

@@ -1,29 +1,29 @@
 # Data Health Report
 
-Snapshot date: 2026-07-18. Regenerate with `npm run data-health:report`.
+Snapshot date: 2026-07-19. Regenerate with `npm run data-health:report`.
 
 ## Scorecard
 
 | Metric | Value |
 | --- | ---: |
 | Manifest records | 134 |
-| Records with structured sources | 6 |
+| Records with structured sources | 9 |
 | Verified records | 39 |
-| Verified with complete provenance | 6 |
+| Verified with complete provenance | 9 |
 | Stale verified records | 0 |
 | Non-English values identical to English | 1411 |
-| Dangling product relationships | 5 |
+| Dangling product relationships | 0 |
 | Model benchmark coverage | 28.1% |
 | Products with pricing | 48/48 |
-| Errors / warnings / info | 0 / 38 / 128 |
+| Errors / warnings / info | 0 / 30 / 125 |
 
 ## Category Breakdown
 
 | Category | Total | Verified | Provenance complete | Stale |
 | --- | ---: | ---: | ---: | ---: |
 | ides | 13 | 0 | 0 | 0 |
-| clis | 20 | 2 | 0 | 0 |
-| extensions | 15 | 3 | 0 | 0 |
+| clis | 20 | 2 | 1 | 0 |
+| extensions | 15 | 3 | 2 | 0 |
 | models | 33 | 28 | 3 | 0 |
 | providers | 13 | 4 | 3 | 0 |
 | vendors | 40 | 2 | 0 | 0 |
@@ -50,9 +50,8 @@ Exact English matches are a triage signal; product names and technical terms can
 
 | Issue | Count |
 | --- | ---: |
-| missing-sources | 128 |
-| verified-without-provenance | 33 |
-| dangling-related-product | 5 |
+| missing-sources | 125 |
+| verified-without-provenance | 30 |
 
 ## Priority Queue
 
@@ -61,15 +60,7 @@ visible in the scorecards and `data/data-health.json`.
 
 | Severity | Issue | Record | Detail |
 | --- | --- | --- | --- |
-| warning | dangling-related-product | extensions/droid | References missing clis/factory. |
-| warning | dangling-related-product | extensions/qoder | References missing ides/qoder-ide. |
-| warning | dangling-related-product | ides/intellij-idea | References missing clis/idea. |
-| warning | dangling-related-product | ides/vscode | References missing clis/code. |
-| warning | dangling-related-product | ides/zed | References missing clis/zed. |
-| warning | verified-without-provenance | clis/claude-code-cli | Verified record is missing sources, review date, reviewer, or confidence. |
 | warning | verified-without-provenance | clis/kilo-code-cli | Verified record is missing sources, review date, reviewer, or confidence. |
-| warning | verified-without-provenance | extensions/claude-code | Verified record is missing sources, review date, reviewer, or confidence. |
-| warning | verified-without-provenance | extensions/gemini-code-assist | Verified record is missing sources, review date, reviewer, or confidence. |
 | warning | verified-without-provenance | extensions/kilo-code | Verified record is missing sources, review date, reviewer, or confidence. |
 | warning | verified-without-provenance | models/claude-opus-4 | Verified record is missing sources, review date, reviewer, or confidence. |
 | warning | verified-without-provenance | models/claude-opus-4-1 | Verified record is missing sources, review date, reviewer, or confidence. |

docs/DATA-TRUST.md

@@ -36,12 +36,12 @@ Example:
 
 ## Current rollout state
 
-Legacy records may have `verified: true` without structured provenance because the boolean predates these fields. Treat those badges as evidence of a prior team review, not as a current freshness guarantee. They are being backfilled category by category; no source or review date should be invented merely to complete the fields. The first official-source batch covers OpenAI, Anthropic, and Google providers plus one representative model from each.
+Legacy records may have `verified: true` without structured provenance because the boolean predates these fields. Treat those badges as evidence of a prior team review, not as a current freshness guarantee. They are being backfilled category by category; no source or review date should be invented merely to complete the fields. The first official-source batch covers OpenAI, Anthropic, and Google providers plus one representative model from each. The second batch covers the Claude Code CLI and IDE integration plus Gemini Code Assist, including current product editions and release information.
 
 For new entries and material updates, a `verified: true` change should include at least one authoritative source, `lastVerifiedAt`, `verifiedBy`, and `confidence`. Official product documentation and pricing pages are preferred over third-party summaries. Benchmark fields should cite the benchmark owner or an official model report.
 
 ## Freshness policy
 
 Run `npm run data-health:report` after manifest or translation changes and commit both generated snapshots. CI runs `npm run data-health:check` to reject invalid or stale snapshots.
 
-The current review thresholds are 30 days for models and providers, 60 days for IDEs, CLIs, and extensions, and 90 days for vendors. Threshold findings remain warnings so that legacy debt stays visible without blocking unrelated work. Network reachability is checked by the separate scheduled URL workflow; source authority and field coverage remain pull-request review responsibilities.
+The current review thresholds are 30 days for models and providers, 60 days for IDEs, CLIs, and extensions, and 90 days for vendors. Threshold findings remain warnings so that legacy debt stays visible without blocking unrelated work. Dangling product relationships are errors because they always point to nonexistent records and can break navigation. Network reachability is checked by the separate scheduled URL workflow; source authority and field coverage remain pull-request review responsibilities.

docs/PROJECT-REVIEW-2026-07-18.md

@@ -184,3 +184,15 @@ evidence; completed items are reflected in the checklists and implementation log
 - Added Axe browser checks for the search dialog, language menu, model comparison tables, and
   expanded mobile navigation, fixing the accessible names, ARIA relationships, decorative content,
   and contrast issues those checks exposed.
+
+### 2026-07-19
+
+- Merged the six project-review delivery PRs into `main` in dependency order after revalidating each
+  layer's independent diff and completing the final combined CI run.
+- Corrected five dangling product relationships, distinguishing actual catalog products from local
+  IDE launch commands, and made future dangling relationships fail the data-health CI check.
+- Added official-source provenance for Claude Code CLI, Claude Code IDE integrations, and Gemini
+  Code Assist; refreshed current documentation, releases, licensing, and product editions where the
+  official sources showed that legacy values had changed.
+- Improved the health snapshot from 6 to 9 records with complete provenance, reduced warnings from
+  38 to 30, and eliminated all dangling relationships.

manifests/clis/claude-code-cli.json

@@ -39,10 +39,40 @@
     }
   },
   "verified": true,
+  "sources": [
+    {
+      "url": "https://code.claude.com/docs/en/how-claude-code-works",
+      "title": "How Claude Code works",
+      "fields": ["name", "description", "websiteUrl", "docsUrl"]
+    },
+    {
+      "url": "https://code.claude.com/docs/en/installation",
+      "title": "Claude Code installation",
+      "fields": ["platforms"]
+    },
+    {
+      "url": "https://github.com/anthropics/claude-code/releases/tag/v2.1.215",
+      "title": "Claude Code v2.1.215 release",
+      "fields": ["latestVersion", "resourceUrls.changelog"]
+    },
+    {
+      "url": "https://claude.com/pricing",
+      "title": "Claude plans and pricing",
+      "fields": ["pricing"]
+    },
+    {
+      "url": "https://code.claude.com/docs/en/mcp",
+      "title": "Claude Code MCP documentation",
+      "fields": ["description", "resourceUrls.mcp"]
+    }
+  ],
+  "lastVerifiedAt": "2026-07-19",
+  "verifiedBy": "codex-agent",
+  "confidence": "medium",
   "websiteUrl": "https://code.claude.com",
-  "docsUrl": "https://docs.claude.com",
+  "docsUrl": "https://code.claude.com/docs",
   "vendor": "Anthropic",
-  "latestVersion": "2.0.56",
+  "latestVersion": "2.1.215",
   "githubUrl": "https://github.com/anthropics/claude-code",
   "license": "Proprietary",
   "pricing": [
@@ -93,7 +123,7 @@
     "download": null,
     "changelog": "https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md",
     "pricing": "https://claude.com/pricing",
-    "mcp": "https://docs.claude.com/en/docs/claude-code/mcp",
+    "mcp": "https://code.claude.com/docs/en/mcp",
     "issue": "https://github.com/anthropics/claude-code/issues"
   },
   "communityUrls": {