@agent-native/core 0.90.11 → 0.91.1

package/corpus/templates/analytics/.agents/skills/data-programs/SKILL.md

@@ -73,7 +73,7 @@ ad-hoc analysis) plus two things: a stored, named identity, and a small
    same dry-run path, no persisted row. Use this while tuning a script before
    calling `save-data-program` again.
 6. **Refresh on demand** with `run-data-program(programId, params?,
-   forceRefresh?, includeRows?)` — this is what the agent calls to get a
+forceRefresh?, includeRows?)` — this is what the agent calls to get a
    compact proof-of-result (`rowCount`, `columns`, `sampleRows`) without
    waiting for a panel view. Pass `includeRows: true` only when you need the
    full (capped) row set back in context.
@@ -101,13 +101,13 @@ addition:
 
 Caps enforced on every run (not configurable per-program):
 
-| Limit | Value |
-| --- | --- |
-| Max emitted rows | 10,000 (rows beyond this are dropped, `truncated: true`) |
-| Max emitted result size | 4 MiB (rows dropped from the end to fit; a single row over 4 MiB is a hard `result_too_large` failure — nothing to safely keep) |
-| Max active programs per app | 200 (archive unused ones to free room) |
-| Minimum refresh TTL | 60,000 ms |
-| Run rows kept per (program, params) | 5 most recent (older ones are pruned automatically) |
+| Limit                               | Value                                                                                                                           |
+| ----------------------------------- | ------------------------------------------------------------------------------------------------------------------------------- |
+| Max emitted rows                    | 10,000 (rows beyond this are dropped, `truncated: true`)                                                                        |
+| Max emitted result size             | 4 MiB (rows dropped from the end to fit; a single row over 4 MiB is a hard `result_too_large` failure — nothing to safely keep) |
+| Max active programs per app         | 200 (archive unused ones to free room)                                                                                          |
+| Minimum refresh TTL                 | 60,000 ms                                                                                                                       |
+| Run rows kept per (program, params) | 5 most recent (older ones are pruned automatically)                                                                             |
 
 Truncation is always honest: a partial result comes back with
 `truncated: true`, never a silent drop.
@@ -118,16 +118,16 @@ Every `(programId, paramsHash)` pair (params are canonicalized and hashed, so
 equivalent param objects share a cache entry) has its own run history. What
 happens on each call to `runDataProgram` / a panel view:
 
-| Situation | Behavior |
-| --- | --- |
-| Fresh cache hit (younger than `refreshTtlMs`, or `refreshMode: "manual"` with any prior success) | Returns cached rows instantly, `cacheHit: true` |
-| Cache is older than the TTL | Re-executes synchronously (panel views get a 25s budget; agent/manual calls get 120s), replacing the cache on success |
-| `refreshMode: "manual"` | Never auto-refreshes; only `forceRefresh: true` (or `manual_refresh` from the UI) re-runs it |
-| No cache yet | Executes synchronously like a normal first fetch |
-| `background: true` program, no fresh cache | Serves the last good run immediately with `stale: true` and enqueues a durable background execution (10-minute budget); the *next* call finalizes it if it has completed |
-| Background program, execution still running, no prior success | `background_pending` failure — the panel shows an explicit "running in background" error card, never a blank chart |
-| Execution fails (timeout, sandbox error, bad `emit()` shape) | Failure result with a structured error code; if a previous successful run exists, it is attached as `lastGoodRun` so the panel can stale-serve instead of going blank |
-| Program was archived (`delete-data-program`) | Explicit `archived` failure — panels show "This data program was archived", never a silent blank |
+| Situation                                                                                        | Behavior                                                                                                                                                                 |
+| ------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| Fresh cache hit (younger than `refreshTtlMs`, or `refreshMode: "manual"` with any prior success) | Returns cached rows instantly, `cacheHit: true`                                                                                                                          |
+| Cache is older than the TTL                                                                      | Re-executes synchronously (panel views get a 25s budget; agent/manual calls get 120s), replacing the cache on success                                                    |
+| `refreshMode: "manual"`                                                                          | Never auto-refreshes; only `forceRefresh: true` (or `manual_refresh` from the UI) re-runs it                                                                             |
+| No cache yet                                                                                     | Executes synchronously like a normal first fetch                                                                                                                         |
+| `background: true` program, no fresh cache                                                       | Serves the last good run immediately with `stale: true` and enqueues a durable background execution (10-minute budget); the _next_ call finalizes it if it has completed |
+| Background program, execution still running, no prior success                                    | `background_pending` failure — the panel shows an explicit "running in background" error card, never a blank chart                                                       |
+| Execution fails (timeout, sandbox error, bad `emit()` shape)                                     | Failure result with a structured error code; if a previous successful run exists, it is attached as `lastGoodRun` so the panel can stale-serve instead of going blank    |
+| Program was archived (`delete-data-program`)                                                     | Explicit `archived` failure — panels show "This data program was archived", never a silent blank                                                                         |
 
 Use `background: true` only for programs that routinely take longer than the
 foreground budget (multi-provider joins over large cohorts, deep pagination).
@@ -136,18 +136,18 @@ serves fresh data faster.
 
 ## Error codes
 
-| Code | Meaning | What to do |
-| --- | --- | --- |
-| `program_not_found` | No program with that id | Check the id via `list-data-programs` |
-| `access_denied` | Caller can't see this program | Don't leak existence; ask the owner to share it |
-| `archived` | Program was soft-deleted | Repoint the panel or unarchive by resaving under the same name |
-| `timeout` | Didn't finish within the run's budget | Reduce scope, page in fewer items, or mark `background: true` |
-| `emit_missing` | Script never called `emit(...)` | Add the `emit(rows, schema?)` call at the end |
-| `emit_shape_invalid` | `emit()` args weren't `(array-of-plain-objects, optional-schema-array)` | Fix the shape; check for a stray second `emit()` call |
-| `result_too_large` | A single row (or the whole result) exceeds the byte cap | Trim large string fields before emitting |
-| `sandbox_error` | Uncaught exception in the script | Read the thrown message; guard optional provider fields |
-| `run_code_unavailable` | The run-code module isn't available in this build | Not something a program author can fix |
-| `background_pending` | Background program has no result yet | Wait and retry, or check `lastGoodRun` if present |
+| Code                   | Meaning                                                                 | What to do                                                     |
+| ---------------------- | ----------------------------------------------------------------------- | -------------------------------------------------------------- |
+| `program_not_found`    | No program with that id                                                 | Check the id via `list-data-programs`                          |
+| `access_denied`        | Caller can't see this program                                           | Don't leak existence; ask the owner to share it                |
+| `archived`             | Program was soft-deleted                                                | Repoint the panel or unarchive by resaving under the same name |
+| `timeout`              | Didn't finish within the run's budget                                   | Reduce scope, page in fewer items, or mark `background: true`  |
+| `emit_missing`         | Script never called `emit(...)`                                         | Add the `emit(rows, schema?)` call at the end                  |
+| `emit_shape_invalid`   | `emit()` args weren't `(array-of-plain-objects, optional-schema-array)` | Fix the shape; check for a stray second `emit()` call          |
+| `result_too_large`     | A single row (or the whole result) exceeds the byte cap                 | Trim large string fields before emitting                       |
+| `sandbox_error`        | Uncaught exception in the script                                        | Read the thrown message; guard optional provider fields        |
+| `run_code_unavailable` | The run-code module isn't available in this build                       | Not something a program author can fix                         |
+| `background_pending`   | Background program has no result yet                                    | Wait and retry, or check `lastGoodRun` if present              |
 
 Every failure is a structured `{ code, message }`, never a bare string — treat
 `code` as the thing to branch on, `message` as the thing to show a human.
@@ -156,7 +156,7 @@ Every failure is a structured `{ code, message }`, never a bare string — treat
 
 - **Credentials are always the viewer's, never the author's.** When a shared
   program's panel is viewed, `providerFetch` inside it resolves auth using the
-  *viewing* user's own configured provider credentials — not the program
+  _viewing_ user's own configured provider credentials — not the program
   author's. A teammate missing a HubSpot key sees a HubSpot auth error on that
   panel, not someone else's data.
 - **Only share programs you trust.** Because execution uses the viewer's
@@ -204,7 +204,8 @@ const HIGH_RISK_SENTIMENTS = ["frustrated", "high_risk_detractor"];
 
 function chunk(items, size) {
   const out = [];
-  for (let i = 0; i < items.length; i += size) out.push(items.slice(i, i + size));
+  for (let i = 0; i < items.length; i += size)
+    out.push(items.slice(i, i + size));
   return out;
 }
 
@@ -217,19 +218,42 @@ async function main() {
     {
       method: "POST",
       body: {
-        filterGroups: [{
-          filters: [
-            { propertyName: "risk_status", operator: "IN", values: riskStatuses },
-            { propertyName: "closedate", operator: "GT", value: String(Date.now()) },
-          ],
-        }],
-        properties: ["dealname", "risk_status", "risk_summary", "risk_category",
-          "hs_next_step", "churn_notes", "total_contract_value",
-          "customer_success_owner", "dealstage", "closedate"],
+        filterGroups: [
+          {
+            filters: [
+              {
+                propertyName: "risk_status",
+                operator: "IN",
+                values: riskStatuses,
+              },
+              {
+                propertyName: "closedate",
+                operator: "GT",
+                value: String(Date.now()),
+              },
+            ],
+          },
+        ],
+        properties: [
+          "dealname",
+          "risk_status",
+          "risk_summary",
+          "risk_category",
+          "hs_next_step",
+          "churn_notes",
+          "total_contract_value",
+          "customer_success_owner",
+          "dealstage",
+          "closedate",
+        ],
         limit: 100,
       },
       itemsPath: "results",
-      pagination: { cursorBodyPath: "after", nextCursorPath: "paging.next.after", maxPages: 20 },
+      pagination: {
+        cursorBodyPath: "after",
+        nextCursorPath: "paging.next.after",
+        maxPages: 20,
+      },
     },
   );
   const deals = dealSearch.items || [];
@@ -241,28 +265,38 @@ async function main() {
   for (const batch of chunk(dealIds, 100)) {
     if (batch.length === 0) continue;
     const assoc = await providerFetch(
-      "hubspot", "/crm/v3/associations/deals/companies/batch/read",
+      "hubspot",
+      "/crm/v3/associations/deals/companies/batch/read",
       { method: "POST", body: { inputs: batch.map((id) => ({ id })) } },
     );
     for (const r of (assoc && assoc.results) || []) {
       const dealId = r && r.from && r.from.id;
-      const companyId = r && Array.isArray(r.to) && r.to.length > 0 ? r.to[0].id : null;
+      const companyId =
+        r && Array.isArray(r.to) && r.to.length > 0 ? r.to[0].id : null;
       if (dealId && companyId) companyByDeal[dealId] = companyId;
     }
   }
 
   // 3. Batched company -> domain lookup.
-  const companyIds = Array.from(new Set(Object.values(companyByDeal))).filter(Boolean);
+  const companyIds = Array.from(new Set(Object.values(companyByDeal))).filter(
+    Boolean,
+  );
   const domainByCompany = {};
   for (const batch of chunk(companyIds, 100)) {
     if (batch.length === 0) continue;
     const companies = await providerFetch(
-      "hubspot", "/crm/v3/objects/companies/batch/read",
-      { method: "POST", body: { inputs: batch.map((id) => ({ id })), properties: ["domain"] } },
+      "hubspot",
+      "/crm/v3/objects/companies/batch/read",
+      {
+        method: "POST",
+        body: { inputs: batch.map((id) => ({ id })), properties: ["domain"] },
+      },
     );
     for (const r of (companies && companies.results) || []) {
-      const domain = r && r.properties && r.properties.domain
-        ? String(r.properties.domain).toLowerCase() : null;
+      const domain =
+        r && r.properties && r.properties.domain
+          ? String(r.properties.domain).toLowerCase()
+          : null;
       if (r && r.id && domain) domainByCompany[r.id] = domain;
     }
   }
@@ -270,15 +304,25 @@ async function main() {
   // 4. A second, unrelated provider — zero bespoke glue action required.
   const pylonAccounts = await providerFetchAll("pylon", "/accounts", {
     itemsPath: "data",
-    pagination: { cursorParam: "cursor", nextCursorPath: "pagination.cursor", maxPages: 20 },
+    pagination: {
+      cursorParam: "cursor",
+      nextCursorPath: "pagination.cursor",
+      maxPages: 20,
+    },
   });
   const sentimentByDomain = {};
   for (const account of pylonAccounts.items || []) {
     if (!account) continue;
-    const domain = typeof account.domain === "string" ? account.domain.toLowerCase() : null;
+    const domain =
+      typeof account.domain === "string" ? account.domain.toLowerCase() : null;
     if (!domain) continue;
-    if (params.enterpriseOnly && account.account_profile !== "Enterprise Active Customer") continue;
-    if (account.general_sentiment) sentimentByDomain[domain] = account.general_sentiment;
+    if (
+      params.enterpriseOnly &&
+      account.account_profile !== "Enterprise Active Customer"
+    )
+      continue;
+    if (account.general_sentiment)
+      sentimentByDomain[domain] = account.general_sentiment;
   }
 
   // 5. Join + emit. csm_name is computed HERE — never baked into a generic
@@ -303,18 +347,27 @@ async function main() {
       closedate: props.closedate || null,
       domain: domain || null,
       pylon_sentiment: sentiment,
-      cross_source_flag: Boolean(domain && HIGH_RISK_SENTIMENTS.includes(sentiment)),
+      cross_source_flag: Boolean(
+        domain && HIGH_RISK_SENTIMENTS.includes(sentiment),
+      ),
     };
   });
 
   emit(rows, [
-    { name: "deal_id", type: "string" }, { name: "deal_name", type: "string" },
-    { name: "risk_status", type: "string" }, { name: "risk_summary", type: "string" },
-    { name: "risk_category", type: "string" }, { name: "next_step", type: "string" },
-    { name: "churn_notes", type: "string" }, { name: "arr", type: "number" },
-    { name: "csm_name", type: "string" }, { name: "dealstage", type: "string" },
-    { name: "closedate", type: "string" }, { name: "domain", type: "string" },
-    { name: "pylon_sentiment", type: "string" }, { name: "cross_source_flag", type: "boolean" },
+    { name: "deal_id", type: "string" },
+    { name: "deal_name", type: "string" },
+    { name: "risk_status", type: "string" },
+    { name: "risk_summary", type: "string" },
+    { name: "risk_category", type: "string" },
+    { name: "next_step", type: "string" },
+    { name: "churn_notes", type: "string" },
+    { name: "arr", type: "number" },
+    { name: "csm_name", type: "string" },
+    { name: "dealstage", type: "string" },
+    { name: "closedate", type: "string" },
+    { name: "domain", type: "string" },
+    { name: "pylon_sentiment", type: "string" },
+    { name: "cross_source_flag", type: "boolean" },
   ]);
 }
 

package/corpus/templates/analytics/.agents/skills/data-querying/SKILL.md

@@ -111,6 +111,7 @@ For complete answers, combine data from multiple sources:
 ## After Completing an Analysis — Capture New Knowledge
 
 When you complete an analysis and discover:
+
 - A new confirmed metric definition or how a field is actually calculated
 - A provider gotcha (wrong column name, API quirk, unexpected behavior)
 - A schema discovery (table exists but wasn't in the dictionary, a column name differs)

package/corpus/templates/analytics/.agents/skills/gong/SKILL.md

@@ -110,8 +110,8 @@ negative. Use this two-step pattern:
    `provider-api-catalog(provider: "gong")` and its `corpusRecipes` if you need
    the exact shape. The canonical request is `POST /calls/transcript` with
    `batch.itemBodyPath: "filter.callIds"`, `batch.responseItemsPath:
-   "callTranscripts"`, `batch.batchSize: 20`, `search.textPaths:
-   ["transcript"]`, and `search.idPaths: ["callId"]`. Feed the staged/discovered
+"callTranscripts"`, `batch.batchSize: 20`, `search.textPaths:
+["transcript"]`, and `search.idPaths: ["callId"]`. Feed the staged/discovered
    call IDs through `batch.inputDatasetId` + `batch.inputValuePath` or through
    `batch.items`.
 
@@ -126,11 +126,11 @@ matches found. Never turn "I inspected a sample" into "no call mentions X".
 
 ## Limits (Current)
 
-| Parameter | Default | Max |
-|---|---|---|
-| `limit` (calls returned) | 8 | 200 |
-| `transcriptLimit` | 3 | 50 |
-| `transcriptMaxChars` | 8 000 | 100 000 |
+| Parameter                | Default | Max     |
+| ------------------------ | ------- | ------- |
+| `limit` (calls returned) | 8       | 200     |
+| `transcriptLimit`        | 3       | 50      |
+| `transcriptMaxChars`     | 8 000   | 100 000 |
 
 For large account deep-dives or competitive analyses spanning many calls, use
 `limit: 50-200` and `transcriptLimit: 20-50`. For very large datasets, the

package/corpus/templates/analytics/.agents/skills/hubspot/SKILL.md

@@ -54,6 +54,7 @@ To discover stage IDs, call `hubspot-pipelines` first and read the `stageId`
 fields in the returned pipeline structure.
 
 Example use: to count deals that reached "Qualified Opportunity" stage in Q1:
+
 ```
 provider-api-request(
   provider: "hubspot",

package/corpus/templates/analytics/.agents/skills/prometheus/SKILL.md

@@ -101,7 +101,7 @@ issues (spikes, outages, errors, performance degradation):
 
 1. **Query actual metrics FIRST** — use Prometheus/Grafana, Sentry, and Cloud
    Logging before looking at code. Real data tells you what happened; code only
-   tells you what *could* happen.
+   tells you what _could_ happen.
 2. **Check upstream dependencies** — many incidents are caused by provider-side
    degradation (LLM APIs, external services), not local code. Query latency
    metrics for each upstream call.

package/corpus/templates/analytics/.builder/skills/bigquery/SKILL.md

@@ -12,7 +12,7 @@ description: >
 **`bigquery` is available directly in the agent's tool list as a native callable tool.**
 
 - If you see `bigquery` in your available tools — **call it directly with your SQL**. Do not use HTTP workarounds, web-request hacks, or scripts as a substitute.
-- The `server/lib/bigquery.ts` description below is the *underlying implementation*. It does **not** mean BigQuery is only accessible via terminal commands or scripts.
+- The `server/lib/bigquery.ts` description below is the _underlying implementation_. It does **not** mean BigQuery is only accessible via terminal commands or scripts.
 - **When uncertain if the tool works, call it — don't reason your way to "it won't work".** Empirically test by calling the tool.
 - Scripts (`pnpm action`) and the server lib are for dashboard UI code and CLI use. The agent calls BigQuery directly via its native tool.
 
@@ -71,16 +71,16 @@ description: >
 
 ### Sigma Blog Metadata Column Mapping
 
-| Cryptic Column | Meaning                  | Example Values                                                    |
-| -------------- | ------------------------ | ----------------------------------------------------------------- |
-| `SUOHFYGIOG`   | Blog URL                 | `https://www.example.com/blog/sample-post`                        |
-| `H5YIATNDT5`   | Author                   | Jane Doe, Alex Chen, Sam Patel, Taylor Kim                        |
-| `ZZJ6XRJAII`   | Publish date (TIMESTAMP) |                                                                   |
-| `FTRKLGZM1R`   | Purpose                  | Acquisition, Awareness                                            |
-| `IFHWPU1IDO`   | Persona                  | Developers, Product Managers, Engineering Leaders, Designers      |
-| `Z52LFY52AK`   | Topic                    | AI, CMS, Web Development, Design                                  |
-| `_DGCBJNKLE`   | Sub-type                 | Tooling, Development, Prototyping                                 |
-| `JQL-G1QE-B`   | Sub-topic                | AI Design, AI Prototyping, AI Tools                               |
+| Cryptic Column | Meaning                  | Example Values                                               |
+| -------------- | ------------------------ | ------------------------------------------------------------ |
+| `SUOHFYGIOG`   | Blog URL                 | `https://www.example.com/blog/sample-post`                   |
+| `H5YIATNDT5`   | Author                   | Jane Doe, Alex Chen, Sam Patel, Taylor Kim                   |
+| `ZZJ6XRJAII`   | Publish date (TIMESTAMP) |                                                              |
+| `FTRKLGZM1R`   | Purpose                  | Acquisition, Awareness                                       |
+| `IFHWPU1IDO`   | Persona                  | Developers, Product Managers, Engineering Leaders, Designers |
+| `Z52LFY52AK`   | Topic                    | AI, CMS, Web Development, Design                             |
+| `_DGCBJNKLE`   | Sub-type                 | Tooling, Development, Prototyping                            |
+| `JQL-G1QE-B`   | Sub-topic                | AI Design, AI Prototyping, AI Tools                          |
 
 **Deduplication**: Table has duplicates (http:// vs https://). Always deduplicate: `REGEXP_EXTRACT(SUOHFYGIOG, r'/blog/([^/?#]+)')` with ROW_NUMBER or DISTINCT.
 
@@ -170,12 +170,12 @@ Use **Amplitude** (`amplitude.EVENTS_182198`) instead of `@app_events` — small
 
 ### Key agent chat event types
 
-| Event                                     | Description                              |
-| ----------------------------------------- | ---------------------------------------- |
-| `agent chat message submitted`            | User sends message in AI chat            |
-| `visual editor ai chat message submitted` | User sends message in Visual Editor AI   |
-| `agent chat message completed`            | AI response completed                    |
-| `agent chat code applied`                 | User applied generated code              |
+| Event                                     | Description                            |
+| ----------------------------------------- | -------------------------------------- |
+| `agent chat message submitted`            | User sends message in AI chat          |
+| `visual editor ai chat message submitted` | User sends message in Visual Editor AI |
+| `agent chat message completed`            | AI response completed                  |
+| `agent chat code applied`                 | User applied generated code            |
 
 ### Customer agent chat message lookup pipeline
 

package/corpus/templates/analytics/.builder/skills/gcloud/SKILL.md

@@ -42,11 +42,11 @@ description: >
 Use `gcloud` for agent-facing Google Cloud work. Do not call
 `/api/gcloud/*` directly from the agent.
 
-| Mode | Args | Description |
-| --- | --- | --- |
-| `services` | | List Cloud Run services and Cloud Functions |
-| `metrics` | `service`, `serviceType`, `metric`, `period`, `extraFilter` | Query Cloud Monitoring |
-| `logs` | `service`, `serviceType`, `severity`, `limit` | Read Cloud Logging |
+| Mode       | Args                                                        | Description                                 |
+| ---------- | ----------------------------------------------------------- | ------------------------------------------- |
+| `services` |                                                             | List Cloud Run services and Cloud Functions |
+| `metrics`  | `service`, `serviceType`, `metric`, `period`, `extraFilter` | Query Cloud Monitoring                      |
+| `logs`     | `service`, `serviceType`, `severity`, `limit`               | Read Cloud Logging                          |
 
 ### Dashboard
 

package/corpus/templates/analytics/.builder/skills/github/SKILL.md

@@ -33,14 +33,14 @@ description: >
 
 ### API Routes
 
-| Route                                                                    | Description                            |
-| ------------------------------------------------------------------------ | -------------------------------------- |
-| `GET /api/github/search?q=...&type=pr\|issue&limit=30`                   | Full GitHub search syntax              |
-| `GET /api/github/pr?owner=...&repo=...&number=...`                       | PR detail with commits, reviews, files |
-| `GET /api/github/issue?owner=...&repo=...&number=...`                    | Issue detail                           |
-| `GET /api/github/prs?owner=...&repo=...&state=open\|closed\|all`         | List repo PRs                          |
+| Route                                                                | Description                            |
+| -------------------------------------------------------------------- | -------------------------------------- |
+| `GET /api/github/search?q=...&type=pr\|issue&limit=30`               | Full GitHub search syntax              |
+| `GET /api/github/pr?owner=...&repo=...&number=...`                   | PR detail with commits, reviews, files |
+| `GET /api/github/issue?owner=...&repo=...&number=...`                | Issue detail                           |
+| `GET /api/github/prs?owner=...&repo=...&state=open\|closed\|all`     | List repo PRs                          |
 | `GET /api/github/org-prs?org=<org>&q=...&state=OPEN\|CLOSED\|MERGED` | Org-wide PR search                     |
-| `POST /api/github/graphql` body: `{ query, variables? }`                 | Raw GraphQL                            |
+| `POST /api/github/graphql` body: `{ query, variables? }`             | Raw GraphQL                            |
 
 ## Script Usage
 

package/corpus/templates/analytics/.builder/skills/gong/SKILL.md

@@ -23,16 +23,16 @@ description: >
 
 ### Exported Functions
 
-| Function                    | Description                                              |
-| --------------------------- | -------------------------------------------------------- |
-| `getCalls(filters?)`        | List calls (cursor-paginated)                            |
-| `getCall(callId)`           | Get single call detail                                   |
-| `getCallTranscript(callId)` | Get one call transcript                                  |
-| `getCallTranscripts(callIds)` | Batch-fetch call transcripts                           |
-| `getUsers()`                | List Gong users                                          |
-| `searchCalls(query, days)`  | List + filter by title and external party name/email/domain |
-| `getCallDetail(callId)`     | Get parties plus Gong brief/key points/outline            |
-| `getEnrichedTranscript(id)` | Transcript mapped to Gong parties and external speakers    |
+| Function                      | Description                                                 |
+| ----------------------------- | ----------------------------------------------------------- |
+| `getCalls(filters?)`          | List calls (cursor-paginated)                               |
+| `getCall(callId)`             | Get single call detail                                      |
+| `getCallTranscript(callId)`   | Get one call transcript                                     |
+| `getCallTranscripts(callIds)` | Batch-fetch call transcripts                                |
+| `getUsers()`                  | List Gong users                                             |
+| `searchCalls(query, days)`    | List + filter by title and external party name/email/domain |
+| `getCallDetail(callId)`       | Get parties plus Gong brief/key points/outline              |
+| `getEnrichedTranscript(id)`   | Transcript mapped to Gong parties and external speakers     |
 
 ### UI API Routes
 
@@ -87,8 +87,8 @@ raw transcript corpus path:
 2. Prefer `provider-corpus-job` with `mode: "batch-search"` against
    `POST /calls/transcript`.
 3. Use `batch.itemBodyPath: "filter.callIds"`, `batch.responseItemsPath:
-   "callTranscripts"`, `batch.batchSize: 20`, `search.textPaths:
-   ["transcript"]`, and `search.idPaths: ["callId"]`.
+"callTranscripts"`, `batch.batchSize: 20`, `search.textPaths:
+["transcript"]`, and `search.idPaths: ["callId"]`.
 4. Join the stored hits back to deals/accounts with `run-code` or staged-dataset
    queries, then report cohort size, call IDs discovered, transcript records
    scanned, hits, errors, and quota gaps.

package/corpus/templates/analytics/.builder/skills/grafana/SKILL.md

@@ -45,13 +45,13 @@ description: >
 Use `grafana` for agent-facing Grafana work. Do not call `/api/grafana/*`
 directly from the agent.
 
-| Mode | Args | Description |
-| --- | --- | --- |
-| `dashboards` | `search` | Search dashboards |
-| `dashboard` | `uid` | Full dashboard JSON |
-| `datasources` | | List datasources |
-| `alerts` | | Alert rules and firing instances |
-| `query` | `datasourceUid`, `queries`, `from`, `to` | Query a datasource |
+| Mode          | Args                                     | Description                      |
+| ------------- | ---------------------------------------- | -------------------------------- |
+| `dashboards`  | `search`                                 | Search dashboards                |
+| `dashboard`   | `uid`                                    | Full dashboard JSON              |
+| `datasources` |                                          | List datasources                 |
+| `alerts`      |                                          | Alert rules and firing instances |
+| `query`       | `datasourceUid`, `queries`, `from`, `to` | Query a datasource               |
 
 ### Dashboard
 

package/corpus/templates/analytics/.builder/skills/sentry/SKILL.md

@@ -34,13 +34,13 @@ description: >
 Use `sentry` for all agent-facing Sentry work. Do not call `/api/sentry/*`
 directly from the agent.
 
-| Mode | Args | Description |
-| --- | --- | --- |
-| `organizations` | | List organizations visible to the token |
-| `issues` | `statsPeriod`, `project`, `query`, `orgSlug` | Frequent issues, sorted by frequency |
-| `projects` | `orgSlug` | List projects |
-| `issue-events` | `issueId`, `orgSlug` | Events for a specific issue |
-| `stats` | `statsPeriod`, `category`, `orgSlug` | Org-level stats |
+| Mode            | Args                                         | Description                             |
+| --------------- | -------------------------------------------- | --------------------------------------- |
+| `organizations` |                                              | List organizations visible to the token |
+| `issues`        | `statsPeriod`, `project`, `query`, `orgSlug` | Frequent issues, sorted by frequency    |
+| `projects`      | `orgSlug`                                    | List projects                           |
+| `issue-events`  | `issueId`, `orgSlug`                         | Events for a specific issue             |
+| `stats`         | `statsPeriod`, `category`, `orgSlug`         | Org-level stats                         |
 
 ### API Routes
 

package/corpus/templates/analytics/.builder/skills/slack/SKILL.md

@@ -35,13 +35,13 @@ description: >
 Use `slack-messages` for agent-facing Slack reads. Do not call
 `/api/slack/*` directly from the agent.
 
-| Mode | Args | Description |
-| --- | --- | --- |
-| `team` | `workspace` | Get workspace info |
-| `channels` | `workspace` | List channels |
-| `history` | `workspace`, `channel`, `limit`, `cursor` | Read channel history |
+| Mode            | Args                                                 | Description            |
+| --------------- | ---------------------------------------------------- | ---------------------- |
+| `team`          | `workspace`                                          | Get workspace info     |
+| `channels`      | `workspace`                                          | List channels          |
+| `history`       | `workspace`, `channel`, `limit`, `cursor`            | Read channel history   |
 | `multi-history` | `workspace`, `channels`, `names`, `limit`, `cursors` | Read multiple channels |
-| `search` | `workspace`, `query` | Search messages |
+| `search`        | `workspace`, `query`                                 | Search messages        |
 
 ## Key Patterns & Gotchas
 

package/corpus/templates/analytics/.builder/skills/stripe/SKILL.md

@@ -22,13 +22,13 @@ description: How to connect to and query the Stripe API for analytics data.
 Use `stripe` for agent-facing Stripe work. Do not call `/api/stripe/*`
 directly from the agent.
 
-| Mode | Args | Description |
-| --- | --- | --- |
-| `billing` | `email`, `customerId`, `query`, `months` | Invoices for a customer in timeframe |
-| `payment-status` | `email`, `customerId`, `query` | Recent charges + payment intents |
-| `refunds` | `email`, `customerId`, `query` | Refunds associated with customer |
-| `subscriptions` | `email`, `customerId`, `query` | Active subscriptions |
-| `billing-by-product` | `email`, `customerId`, `query`, `months` | Billing aggregated by product |
+| Mode                 | Args                                     | Description                          |
+| -------------------- | ---------------------------------------- | ------------------------------------ |
+| `billing`            | `email`, `customerId`, `query`, `months` | Invoices for a customer in timeframe |
+| `payment-status`     | `email`, `customerId`, `query`           | Recent charges + payment intents     |
+| `refunds`            | `email`, `customerId`, `query`           | Refunds associated with customer     |
+| `subscriptions`      | `email`, `customerId`, `query`           | Active subscriptions                 |
+| `billing-by-product` | `email`, `customerId`, `query`, `months` | Billing aggregated by product        |
 
 ## API Routes
 

package/corpus/templates/analytics/AGENTS.md

@@ -159,8 +159,11 @@ details live in `.agents/skills/`.
   context.
 - `navigate` moves the user to the relevant analytics view, including
   `view="catalog"` for the template catalog, `view="sessions"` for session
-  replay, and `view="agents"` / `agentsView="database"` with optional
-  `dbAdminConnectionId` for agent monitoring or connected app database admin.
+  replay, `view="monitoring"` with `monitoringView="uptime|errors"` (plus the
+  `monitorId`, `statusPageId`, or `errorIssueId` deep links) for uptime checks,
+  public status pages, or error triage, and `view="agents"` /
+  `agentsView="database"` with optional `dbAdminConnectionId` for agent
+  monitoring or connected app database admin.
 - Use `view-screen` when the active dashboard/chart context is unclear.
 
 ## Session Replay
@@ -201,6 +204,48 @@ details live in `.agents/skills/`.
   `/sessions/:recordingId`; rows that only include `session_id` can link to a
   filtered `/sessions` search.
 
+## Monitoring
+
+- `/monitoring` is the Monitoring tab (`app/routes/monitoring._index.tsx` →
+  `app/pages/monitoring/MonitoringPage.tsx`), a thin shell hosting two
+  independently-owned panels selected by `?view=uptime|errors` (defaults to
+  uptime). `navigation` mirrors it as `view="monitoring"` with `monitoringView`
+  (plus `monitorId`/`errorIssueId` when a row is open); each panel also writes
+  richer selection to the `monitoring` application-state key.
+- Uptime (`app/pages/monitoring/UptimePanel.tsx`,
+  `app/pages/monitoring/uptime/**`) manages synthetic HTTP checks with
+  alerting. Actions: `list-monitors`, `get-monitor`, `save-monitor`,
+  `run-monitor-check`, `delete-monitor`. Checks/alerting run server-side in
+  `server/lib/uptime-monitors.ts` (sweep job `server/jobs/uptime-monitors.ts`,
+  scheduler `server/plugins/uptime-monitor-jobs.ts`) over
+  `server/db/schema-monitoring.ts`. Deep links: list `?view=uptime`, detail
+  `?view=uptime&monitor=<id>`, create `?view=uptime&monitor=new`, edit
+  `?view=uptime&monitor=<id>&edit=1`. See `docs/uptime-monitoring.md`.
+- Status pages (`app/pages/monitoring/uptime/status-pages/**`) are a config
+  sub-view under Uptime that bundle chosen monitors under a public
+  `/status/<slug>` page. Actions: `list-status-pages`, `get-status-page`,
+  `save-status-page`, `delete-status-page`, `add-status-page-monitor`,
+  `remove-status-page-monitor`, `reorder-status-page-monitors`, plus the
+  unauthenticated `get-public-status-page`. Owner-scoped CRUD and the sanitized
+  public projection live in `server/lib/status-pages.ts` over
+  `server/db/schema-monitoring.ts`. Deep links: index
+  `?view=uptime&statuspage=list`, create `?view=uptime&statuspage=new`, edit
+  `?view=uptime&statuspage=<id>`.
+- Errors (`app/pages/monitoring/ErrorsPanel.tsx`,
+  `app/pages/monitoring/errors/**`) is Sentry-style exception triage grouped
+  into issues by fingerprint. Actions: `list-error-issues`, `get-error-issue`,
+  `resolve-error-issue`, `capture-test-error`, `match-error-issues`.
+  Ingest/grouping lives in `server/lib/error-capture.ts` over
+  `server/db/schema-errors.ts`. Browser capture uses the SDK from
+  `@agent-native/core/client` (`captureException` / `captureMessage` /
+  `addErrorBreadcrumb`), auto-enabled by `configureTracking` and transported
+  through the first-party analytics ingest as a `$exception` event. Deep link:
+  `?view=errors&issue=<id>`. See `docs/error-capture.md`.
+- Session replay ↔ Errors: a recording's devtools Console error lines link to
+  the grouped issue at `/monitoring?view=errors&issue=<id>`, resolved by
+  `match-error-issues` (exact fingerprint match, no heuristics); issues link
+  back to the originating recording at `/sessions/<recordingId>`.
+
 ## Dashboard Template Catalog
 
 - To build or extend a LARGE first-party dashboard, prefer `compose-dashboard`: