@sentry/junior-datadog 0.30.0 → 0.31.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sentry/junior-datadog",
-  "version": "0.30.0",
+  "version": "0.31.0",
   "private": false,
   "publishConfig": {
     "access": "public"

package/skills/datadog/SKILL.md

@@ -1,12 +1,11 @@
 ---
 name: datadog
 description: Query live Datadog telemetry (logs, metrics, traces, spans, monitors, incidents, dashboards, services, hosts) through Datadog's hosted MCP server. Use when users ask to investigate production behavior in Datadog — searching logs, checking monitor status, inspecting traces or spans, looking up incidents, finding services, or correlating metrics. Do not use it for Sentry issues, repository/source-code work, or ticketing.
-uses-config: datadog.env datadog.service
 ---
 
 # Datadog Operations
 
-Use this skill for Datadog observability investigations in the harness.
+Use this skill for Datadog observability investigations.
 
 ## Reference loading
 
@@ -29,10 +28,8 @@ Load references conditionally based on the request:
 - If the request refers to an earlier telemetry item indirectly (an incident, trace, or monitor already mentioned in the thread), inspect the current thread for the existing ID or URL before asking the user to restate it.
 - Ask one concise follow-up only when a search is genuinely under-specified, for example when the user asks about "errors" with no env, service, or time window hint and the thread has no prior context.
 
-2. Use the active Datadog MCP tools:
+2. Use the active Datadog tools:
 
-- `loadSkill` returns `available_tools` for this skill, including the exact `tool_name` values and input schemas exposed in this turn.
-- Call those exact tool names directly. Use `searchTools` only if you need to rediscover or filter the active Datadog tools later in the same turn.
 - Start narrow: pick the single most direct tool for the request before reaching for broader search.
   - Known incident ID → `get_datadog_incident`
   - Known trace ID → `get_datadog_trace`
@@ -62,7 +59,6 @@ Load references conditionally based on the request:
 
 - Read-only only in this skill. Do not create, edit, mute, or resolve monitors, incidents, notebooks, dashboards, SLOs, or feature flags — the plugin intentionally does not expose those tools.
 - Log, RUM, APM, and incident payloads can contain PII or sensitive customer data. Quote only the minimum needed to answer the question. Do not paste full raw log bodies or span payloads when a summary plus a deep link is enough.
-- If Datadog authorization is required, let the MCP OAuth flow pause and resume the thread automatically instead of asking the user to handle credentials manually.
 - If a Datadog tool returns a generic `403`, `permission denied`, or similar, stop and tell the user the current Datadog connection could not access the requested resource. Do not guess at missing RBAC scopes.
 - If Datadog responds with `429 Too Many Requests`, wait briefly and retry the same query once. If it still fails, report the throttle and stop.
 - For large traces that the server marks as truncated, report that fact; do not pretend the shown spans are complete.

package/skills/datadog/references/api-surface.md

@@ -2,14 +2,6 @@
 
 Use this reference for any Datadog operation.
 
-## Runtime contract
-
-- `loadSkill` returns `available_tools` for this skill, including the exact Datadog MCP `tool_name` values exposed in the current turn.
-- Call those exact `tool_name` values directly.
-- Use `searchTools` only when you need to rediscover or filter the active Datadog tools later in the same turn.
-- Do not hardcode raw Datadog MCP tool names in advance. Tool discovery is part of the workflow.
-- Return concrete findings plus Datadog deep links for navigation.
-
 ## Provider surface
 
 The packaged plugin points at Datadog's hosted remote MCP server and enables the `core`, `apm`, and `error-tracking` toolsets. Tool exposure is intentionally limited to the read-oriented surface below.
@@ -59,34 +51,6 @@ If a user asks for a mutation, stop and explain that this skill is read-only.
 | "Which hosts are unhealthy?"                     | `search_datadog_hosts` filtered by health/tags.                                                                                                    |
 | "Find slow page loads."                          | `search_datadog_rum_events` with a page/speed filter.                                                                                              |
 
-## Config helpers
-
-Use these commands only when the user explicitly asks to inspect or store Datadog defaults for the current conversation/channel.
-
-Resolve env default:
-
-```bash
-jr-rpc config get datadog.env
-```
-
-Set env default:
-
-```bash
-jr-rpc config set datadog.env prod
-```
-
-Resolve service default:
-
-```bash
-jr-rpc config get datadog.service
-```
-
-Set service default:
-
-```bash
-jr-rpc config set datadog.service checkout
-```
-
 ## Content expectations
 
 - Translate Slack-thread wording into stable observability language (env, service, status, span, monitor, incident, host).

package/skills/datadog/references/common-use-cases.md

@@ -79,6 +79,4 @@ Use these patterns to shape concrete Datadog requests.
 
 ## 13. Storing channel defaults
 
-- Use `jr-rpc config set datadog.env <env>` only when the user explicitly asks to store an env default for the conversation/channel.
-- Use `jr-rpc config set datadog.service <service>` only when the user explicitly asks to store a service default for the conversation/channel.
 - Treat both defaults as optional fallbacks. Explicit user input wins whenever a request names a different env or service.

package/skills/datadog/references/troubleshooting-workarounds.md

@@ -2,14 +2,6 @@
 
 Use this reference when Datadog MCP calls fail or return unexpected results.
 
-## Authentication and connection
-
-| Symptom                                                            | Likely cause                                                | What to do                                                                                                                     |
-| ------------------------------------------------------------------ | ----------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------ |
-| Tool call returns an authorization-required signal before running. | User has not yet completed the Datadog OAuth flow in Slack. | Let the runtime DM the user the authorization link and pause the turn. Do not prompt for credentials manually.                 |
-| Tool call returned `401` mid-session.                              | OAuth token expired or was revoked.                         | Expect Junior's MCP layer to resurface the authorization flow. Retry once the user has re-authorized; do not loop before that. |
-| OAuth callback did not resume the thread.                          | User closed the browser before the redirect completed.      | Ask the user to retry the request — the OAuth flow will restart and complete if they finish it this time.                      |
-
 ## Permission and scope errors
 
 - A Datadog API returning `403 Forbidden` or `permission denied` means the user's Datadog role cannot read that resource (metrics, APM, incidents, RUM, etc.).