@sentry/junior-sentry 0.24.1 → 0.26.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sentry/junior-sentry",
-  "version": "0.24.1",
+  "version": "0.26.0",
   "private": false,
   "publishConfig": {
     "access": "public"

package/skills/sentry/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: sentry
-description: Query Sentry telemetry (issues, events, replays, traces) and generate deep links scoped to users or timeframes. This skill should be used when users ask to investigate bugs, search errors, find replays, or look up Sentry data.
-requires-capabilities: sentry.api
+description: Query live Sentry telemetry (issues, events, replays, traces) and generate deep links scoped to users or timeframes. Use this skill when users ask to investigate live Sentry data, search errors, find replays, inspect traces, or look up Sentry issues/events. Do not use it for repository/source-code/PR tasks, even when the topic concerns Sentry products.
 uses-config: sentry.org sentry.project
 allowed-tools: bash
 ---
@@ -22,11 +21,11 @@ Use this skill for Sentry investigation workflows in the harness.
 2. Execute via CLI:
 
 - Use `sentry <command>` for structured queries.
-- The CLI reads `SENTRY_AUTH_TOKEN` from env after the runtime enables the declared Sentry capability for this turn.
+- The runtime injects `SENTRY_AUTH_TOKEN` automatically for authenticated `sentry` CLI commands in this skill.
 - Read [references/cli-commands.md](references/cli-commands.md) for command shapes and flags.
 - Read [references/sandbox-runtime.md](references/sandbox-runtime.md) before relying on sandbox credentials.
-- If a Sentry API call returns `401`, or clearly says the token is invalid, expired, revoked, or unauthorized, run `jr-rpc delete-token sentry` to clear the stale token, then retry after re-enabling the declared capability.
-- If a Sentry API call explicitly says `missing scope`, `missing scopes`, or `insufficient scope`, run `jr-rpc delete-token sentry` to clear the outdated grant, then retry after re-enabling the declared capability.
+- If a Sentry API call returns `401`, or clearly says the token is invalid, expired, revoked, or unauthorized, rerun the real Sentry command once and let the runtime trigger a reconnect flow when needed.
+- If a Sentry API call explicitly says `missing scope`, `missing scopes`, or `insufficient scope`, rerun the real Sentry command once and let the runtime trigger a reconnect flow when needed.
 - If a Sentry API call returns a generic `403`, `permission denied`, or otherwise indicates missing org/project access without naming missing scopes, stop and tell the user the current Sentry connection could not access the requested Sentry data.
 - Only mention a specific missing scope when the CLI or API error explicitly names that scope. Do not guess scope names from a generic `403`.
 
@@ -47,3 +46,4 @@ Use this skill for Sentry investigation workflows in the harness.
 - Do not print credential values.
 - If org is missing and needed, ask the user.
 - Prefer deep links over raw data dumps when linking to Sentry web UI.
+- Do not use this skill for repository/source-code/commit/branch/pull-request work, even if the user mentions a Sentry feature or product area.

package/skills/sentry/references/cli-commands.md

@@ -32,4 +32,4 @@ Lists organizations accessible with current token.
 - `--project PROJECT`: Project slug.
 - `--log-level`: `debug`, `info`, `warn`, `error`.
 
-Only use commands listed in this reference during normal skill execution. If a command reports explicit missing scopes, reconnect the Sentry account to refresh the grant. Treat generic permission or org/project access errors as access problems rather than retryable auth refresh problems.
+Only use commands listed in this reference during normal skill execution. If a command reports expired, revoked, or invalid authorization, reconnect the Sentry account and retry. Treat generic permission or org/project access errors as access problems rather than reconnect signals.

package/skills/sentry/references/sandbox-runtime.md

@@ -11,6 +11,6 @@ This skill runs in the harness sandbox (`node22`) and commands execute via the `
 
 ## Credential strategy
 
-1. Issue credentials with `jr-rpc issue-credential sentry.api` before executing commands.
+1. After the Sentry skill is loaded, authenticated `sentry <command>` calls receive `SENTRY_AUTH_TOKEN` automatically for the current turn.
 2. Run CLI commands: `sentry <command>`.
 3. Credentials are scoped per command execution. Do not persist tokens in files.