Merge branch 'main' into fix/run-event-schema-v3

Author: bharathkumar39293

.changeset/fix-dev-build-dir-leak.md

@@ -0,0 +1,5 @@
+---
+"trigger.dev": patch
+---
+
+Fix dev CLI leaking build directories on rebuild, causing disk space accumulation. Deprecated workers are now pruned (capped at 2 retained) when no active runs reference them. The watchdog process also cleans up `.trigger/tmp/` when the dev CLI is killed ungracefully (e.g. SIGKILL from pnpm).

.changeset/fix-list-deploys-nullable.md

@@ -0,0 +1,5 @@
+---
+"@trigger.dev/core": patch
+---
+
+Fix `list_deploys` MCP tool failing when deployments have null `runtime` or `runtimeVersion` fields.

.changeset/llm-metadata-run-tags.md

@@ -0,0 +1,5 @@
+---
+"@trigger.dev/core": patch
+---
+
+Propagate run tags to span attributes so they can be extracted server-side for LLM cost attribution metadata.

.changeset/mcp-query-tools.md

@@ -0,0 +1,42 @@
+---
+"@trigger.dev/core": patch
+"trigger.dev": patch
+---
+
+MCP server improvements: new tools, bug fixes, and new flags.
+
+**New tools:**
+- `get_query_schema` — discover available TRQL tables and columns
+- `query` — execute TRQL queries against your data
+- `list_dashboards` — list built-in dashboards and their widgets
+- `run_dashboard_query` — execute a single dashboard widget query
+- `whoami` — show current profile, user, and API URL
+- `list_profiles` — list all configured CLI profiles
+- `switch_profile` — switch active profile for the MCP session
+- `start_dev_server` — start `trigger dev` in the background and stream output
+- `stop_dev_server` — stop the running dev server
+- `dev_server_status` — check dev server status and view recent logs
+
+**New API endpoints:**
+- `GET /api/v1/query/schema` — query table schema discovery
+- `GET /api/v1/query/dashboards` — list built-in dashboards
+
+**New features:**
+- `--readonly` flag hides write tools (`deploy`, `trigger_task`, `cancel_run`) so the AI cannot make changes
+- `read:query` JWT scope for query endpoint authorization
+- `get_run_details` trace output is now paginated with cursor support
+- MCP tool annotations (`readOnlyHint`, `destructiveHint`) for all tools
+
+**Bug fixes:**
+- Fixed `search_docs` tool failing due to renamed upstream Mintlify tool (`SearchTriggerDev` → `search_trigger_dev`)
+- Fixed `list_deploys` failing when deployments have null `runtime`/`runtimeVersion` fields (#3139)
+- Fixed `list_preview_branches` crashing due to incorrect response shape access
+- Fixed `metrics` table column documented as `value` instead of `metric_value` in query docs
+- Fixed dev CLI leaking build directories on rebuild — deprecated workers now clean up their build dirs when their last run completes
+
+**Context optimizations:**
+- `get_query_schema` now requires a table name and returns only one table's schema (was returning all tables)
+- `get_current_worker` no longer inlines payload schemas; use new `get_task_schema` tool instead
+- Query results formatted as text tables instead of JSON (~50% fewer tokens)
+- `cancel_run`, `list_deploys`, `list_preview_branches` formatted as text instead of raw JSON
+- Schema and dashboard API responses cached to avoid redundant fetches

.github/VOUCHED.td

@@ -15,4 +15,5 @@ isshaddad
 gautamsi
 capaj
 chengzp
-bharathkumar39293
+bharathkumar39293
+bhekanik

.server-changes/allow-rollbacks-promote-api.md

@@ -0,0 +1,6 @@
+---
+area: webapp
+type: feature
+---
+
+Add allowRollbacks query param to the promote deployment API to enable version downgrades

.server-changes/fix-batch-waitpoint-lock-contention.md

@@ -0,0 +1,6 @@
+---
+area: webapp
+type: fix
+---
+
+Reduce lock contention when processing large `batchTriggerAndWait` batches. Previously, each batch item acquired a Redis lock on the parent run to insert a `TaskRunWaitpoint` row, causing `LockAcquisitionTimeoutError` with high concurrency (880 errors/24h in prod). Since `blockRunWithCreatedBatch` already transitions the parent to `EXECUTING_WITH_WAITPOINTS` before items are processed, the per-item lock is unnecessary. The new `blockRunWithWaitpointLockless` method performs only the idempotent CTE insert without acquiring the lock.

.server-changes/llm-cost-tracking.md

@@ -0,0 +1,6 @@
+---
+area: webapp
+type: feature
+---
+
+Add automatic LLM cost calculation for spans with GenAI semantic conventions. When a span arrives with `gen_ai.response.model` and token usage data, costs are calculated from an in-memory pricing registry backed by Postgres and dual-written to both span attributes (`trigger.llm.*`) and a new `llm_metrics_v1` ClickHouse table that captures usage, cost, performance (TTFC, tokens/sec), and behavioral (finish reason, operation type) metrics.

apps/webapp/app/assets/icons/AiProviderIcons.tsx

@@ -0,0 +1,12 @@
+export function AnthropicLogoIcon({ className }: { className?: string }) {
+  return (
+    <svg
+      className={className}
+      viewBox="0 0 24 24"
+      fill="currentColor"
+      xmlns="http://www.w3.org/2000/svg"
+    >
+      <path d="M17.3041 3.541h-3.6718l6.696 16.918H24Zm-10.6082 0L0 20.459h3.7442l1.3693-3.5527h7.0052l1.3693 3.5528h3.7442L10.5363 3.5409Zm-.3712 10.2232 2.2914-5.9456 2.2914 5.9456Z" />
+    </svg>
+  );
+}