Katia Bulatova
4569657923
## What & why This is the system behind the Dashboard Agent — an assistant that answers questions about a project's runs, errors, queues, deploys and health, and can investigate failures end to end. The agent runs as a chat.agent task in its own Trigger project. It has no access to the main database or ClickHouse; all platform data is read through the public API using a delegated, read-only user token. Everything here is behind `canAccessDashboardAgent` and inert with the flag off. The UI that mounts the panel lands in #4529. ## Stack `#4418` (this, base) ← `#4529` UI ← `#4525` Watch ← `#4516` storybook gallery. The scenario/contract reference for the whole stack is `internal-packages/dashboard-agent/GUIDEBOOK.md` (it lands on the Watch branch): it states, per feature, what makes each thing happen and where that is decided. ## What's inside **Agent runtime and tools** — `internal-packages/dashboard-agent`: prompt, tool set (API reads, TRQL query, docs, navigation, evidence/investigations, repo source), conversation compaction, a prompt-prefix token budget pinned by snapshot test, and sampled LLM-judged turn evals. The package cannot import webapp server code, which is what makes the "no DB access" claim structural rather than a convention. **Contracts** — `internal-packages/dashboard-agent-contracts`: `trigger://` URIs, intents, and the block envelope every rendered card travels in. **Conversation store** — `internal-packages/dashboard-agent-db`: drizzle over postgres-js in its own `trigger_dashboard_agent` Postgres schema, plus one additive migration. **Auth boundary** — the user-actor token gains an optional environment claim; one guard (`userActorEnvironment.server.ts`) enforces it so routes don't each re-derive the rule. Token minting, cap ceiling, and the RBAC fallback path for self-hosted. **Transport** — webapp resource routes that mint the token and proxy each turn, and SDK-side mid-turn reconnect. **Public API the agent reads through** — orgs, projects, environments, runs, queue metrics, workers, a run's commit metadata, repo snapshot, reports, and `POST /api/v1/query`. **Reports** — the health report's layout is declared once and shared by the card, the markdown surface and the JSON/MCP surface, so the same report reads the same in the dashboard, the terminal and an editor. **Block renderers** — the report and investigation cards the flows above already emit (`app/components/dashboard-agent/`). The panel that hosts them, and the rest of the chat UI, is #4529. **Query safety and CSP** — see below. ## Key decisions - **The agent is a separate Trigger project, not webapp code.** It reads platform data over the public API with a delegated user-actor token whose `cap` ceilings it to read scopes. No Prisma, no ClickHouse, no webapp imports. - **The PAT-only auth helper now refuses user-actor tokens.** This is an intentional behavioral change: its callers consume only a bare userId and do not enforce delegated-token capabilities. Actor-aware routes continue through the scoped route builders instead. - **RBAC fallback builds a delegated token's ability from its own cap**, never the blanket ability a PAT gets (read-only when the token declares none). Without this, the agent's read-only cap would buy a write JWT on self-hosted. - **Org creation checks RBAC only for user-actor tokens, and only after the env gate**, so an install with `ORG_CREATION_API_ENABLED` off returns 404 rather than 403, and an ordinary PAT never consults an ability the route has no org to scope. Both orderings are pinned by test. - **The query path is read-only in depth.** TRQL rejects write statements at the grammar level (they don't parse, rather than being filtered), ClickHouse runs with `readonly=1`, and the org/project/env filters are injected server-side from the credential — the request body cannot widen scope. An unparseable query denies instead of falling through to the permissive resource. - **Document-wide img-src CSP.** Remote images are an outbound-request/exfiltration surface, so the policy permits only own-origin/data/blob, the required SSO avatar hosts, and the favicon endpoint. Operators can add exact origins through CSP_IMG_SRC_ALLOWLIST; wildcard hosts and bare schemes are intentionally not allowed. - **The chat transport reconnects on a mid-turn EOF** (`@trigger.dev/sdk`). A body that ends without a turn-complete is terminal only when the server says `X-Session-Settled: true`; otherwise the transport resubscribes from `lastEventId` with bounded backoff, and any record re-earns the budget. Previously a closed long-poll window or a proxy restart left the reply stuck as if still generating. - **Conversations live in their own datastore**, schema-scoped and foreign-key-free (it references `organizationId`/`userId` by id, because in cloud it is a different database). It is a display read-model for the History tab and transport resume; `chat.agent`'s object-store snapshot remains the model's source of truth. - **Deterministic first.** Reports and health checks contain no LLM — they are computed from the same data the dashboard shows, and the model only narrates and links them. That is what makes a number in an answer auditable. ## Testing - 63 new test files, run with `pnpm run test --filter webapp` and per-package vitest. Heaviest coverage on the auth boundary (`userActorPatOnlyBoundary`, `userActorTokenClaimsAndScopes`, `contextlessPatRoutes`, `rbacFallbackBranch`), TRQL read-only, the report layout, and the SDK reconnect. - The agent package has a separate eval lane (`pnpm run test:evals`, `vitest.eval.config.ts`) that hits the real model, so it never runs in `pnpm test`. - Live-tested against a local stack scenario by scenario; the GUIDEBOOK lists the condition each behaviour is expected under, which is what those runs were checked against. ## Changelog `.server-changes/dashboard-agent.md`, plus changesets for `@trigger.dev/core` (report schemas), `@trigger.dev/sdk` (chat reconnect) and the CLI's `mint-token` help text.
Server Changes
This directory tracks changes to server-only components (webapp, supervisor, etc.) that are not captured by changesets. Changesets only track published npm packages — server changes would otherwise go undocumented.
When to add a file
Server-only PRs: If your PR only changes apps/webapp/, apps/supervisor/, or other server components (and does NOT change anything in packages/), add a .server-changes/ file.
Mixed PRs (both packages and server): Just add a changeset as usual. No .server-changes/ file needed — the changeset covers it.
Package-only PRs: Just add a changeset as usual.
File format
Create a markdown file with a descriptive name:
.server-changes/fix-batch-queue-stalls.md
With this format:
---
area: webapp
type: fix
---
Speed up batch queue processing by removing stalls and fixing retry race
Fields
- area (required):
webapp|supervisor - type (required):
feature|fix|improvement|breaking
Description
The body text (below the frontmatter) is a one-line description of the change. Keep it concise — it will appear in release notes.
Writing guidance
These entries are public-facing - they ship verbatim in user-visible release notes. A few rules to keep them clean:
- Write for the user, not the reviewer. Lead with what the user notices or has to do. If a reader who doesn't know the codebase can't tell what changed for them, rewrite it.
- One sentence is usually enough. The body is the bullet in the changelog. If you need a paragraph, you're probably describing the implementation rather than the change.
- Describe behavior, not implementation. Skip internal scopes, middleware names, library specifics, framework internals. Users care about what's different for them, not how it's wired.
- Never name internal tools or infra. Observability stacks, internal services, infra components, monitoring backends, CI surfaces, AWS specifics - none of these belong in user-facing notes.
Before / after:
- ❌ "The image verification step now parses the manifest's layer media types and returns a new result the finalizer rejects." (describes the wiring; a user can't act on it)
- ✅ "Deploying with an outdated CLI could produce an image that fails to start on every run. These deploys are now stopped before going live, with a message asking you to upgrade the CLI and re-deploy." (what the user sees and does)
Lifecycle
- Engineer adds a
.server-changes/file in their PR - Files accumulate on
mainas PRs merge - The changeset release PR includes these in its summary
- After the release merges, CI cleans up the consumed files
Examples
New feature:
---
area: webapp
type: feature
---
TRQL query language and the Query page
Bug fix:
---
area: webapp
type: fix
---
Fix schedule limit counting for orgs with custom limits
Improvement:
---
area: webapp
type: improvement
---
Use the replica for API auth queries to reduce primary load