@axlsdk/studio 0.15.0 → 0.16.0

package/README.md

@@ -174,9 +174,9 @@ Single endpoint at `ws://localhost:4400/ws` with channel multiplexing:
 { "type": "event", "channel": "trace:abc-123", "data": { ... } }
 ```
 
-Channels: `execution:{id}`, `trace:{id}`, `trace:*`, `eval:{id}`, `eval:{evalRunId}`, `eval:*`, `costs`, `eval-trends`, `workflow-stats`, `trace-stats`, `decisions`. Execution and eval channels have replay buffering — late subscribers receive the full event history (capped at 500 events, cleaned up 30s after stream completes). Aggregate channels (`costs`, `eval-trends`, `workflow-stats`, `trace-stats`) broadcast `{ snapshots: Record<WindowId, State>, updatedAt }` on every fold or rebuild.
+Channels: `execution:{id}`, `trace:{id}`, `trace:*`, `eval:{id}`, `eval:{evalRunId}`, `eval:*`, `costs`, `eval-trends`, `workflow-stats`, `trace-stats`, `decisions`. Execution and eval channels have replay buffering — late subscribers receive the full event history (capped at 1000 events by default; tunable via `bufferCaps`, see below). Buffers are cleaned up 30s after the stream completes. Aggregate channels (`costs`, `eval-trends`, `workflow-stats`, `trace-stats`) broadcast `{ snapshots: Record<WindowId, State>, updatedAt }` on every fold or rebuild.
 
-**Outbound frame budget.** The WS broadcast layer enforces a 64KB soft cap via `truncateIfOversized`. Oversized verbose-mode `agent_call.data.messages` snapshots are replaced with a `{ __truncated: true, originalBytes, maxBytes, hint }` placeholder that preserves the event's `type`/`step`/`agent`/`tool` so the Trace Explorer still renders the row. The 64KB threshold matches the inbound message reject limit in the WS protocol (shared constant).
+**Outbound frame budget.** The WS broadcast layer enforces a 64KB soft cap via `truncateIfOversized`. Oversized verbose-mode `agent_call_end.data.messages` snapshots are replaced with a `{ __truncated: true, originalBytes, maxBytes, hint }` placeholder that preserves the event's `type`/`step`/`agent`/`tool` so the Trace Explorer still renders the row. The 64KB threshold matches the inbound message reject limit in the WS protocol (shared constant).
 
 ### Migrating from 0.14
 
@@ -225,6 +225,7 @@ studio.upgradeWebSocket(server);
 | `filterTraceEvent` | `(event, metadata) => boolean` | — | Per-connection broadcast filter for multi-tenant deployments. Called on every outbound trace event (and on replay buffer events for late subscribers, so historical cross-tenant events can't leak on reconnect). Predicate errors are fail-closed — event is dropped |
 | `readOnly` | `boolean` | `false` | Disable all mutating endpoints. `POST /api/evals/compare` is allowed (pure computation); `POST /api/evals/import`, `POST /api/evals/:name/run`, `POST /api/evals/:name/rescore`, `POST /api/evals/runs/:evalRunId/cancel`, and `DELETE /api/evals/history/:id` are blocked |
 | `evals` | `string \| string[] \| { files, conditions? }` | — | Lazy-load eval files for the Eval Runner panel |
+| `bufferCaps` | `{ maxEventsPerBuffer?, maxBytesPerBuffer?, maxActiveBuffers? }` | `{ 1000, 4 MiB, 256 }` | Override the default WebSocket replay-buffer resource caps for high-churn deployments. Worst-case memory is roughly `maxActiveBuffers × maxBytesPerBuffer` (≈1 GiB at defaults). Terminal `done`/`error` events are always buffered regardless of caps |
 
 ### Return value
 
@@ -443,11 +444,11 @@ Lazy-loaded evals coexist with evals registered directly via `runtime.registerEv
 When the runtime is constructed with `config.trace.redact: true`, Studio scrubs user/LLM content at three layers — trace events at emission, REST route responses at serialization, and WebSocket broadcasts at send time — while preserving structural metadata (IDs, keys, agent/tool/workflow names, roles, cost/token/duration metrics, timestamps).
 
 ```typescript
-const runtime = new AxlRuntime({ config: { trace: { redact: true } } });
+const runtime = new AxlRuntime({ trace: { redact: true } });
 const studio = createStudioMiddleware({ runtime });
 ```
 
-Under `redact: true`, the following Studio endpoints scrub user content server-side before responding: `GET /api/executions{,/:id}`, `GET /api/memory/:scope{,/:key}` (keys preserved so Memory Browser stays navigable), `GET /api/sessions/:id`, `GET /api/evals/history`, `POST /api/evals/:name/run` (sync), `POST /api/evals/:name/rescore`, `GET /api/decisions`, `POST /api/tools/:name/test`, `POST /api/workflows/:name/execute` (sync); streaming WS broadcasts on `/workflows/:name/execute` with `stream: true` and `/api/playground/chat` also scrub `StreamEvent` content before send.
+Under `redact: true`, the following Studio endpoints scrub user content server-side before responding: `GET /api/executions{,/:id}`, `GET /api/memory/:scope{,/:key}` (keys preserved so Memory Browser stays navigable), `GET /api/sessions/:id`, `GET /api/evals/history`, `POST /api/evals/:name/run` (sync), `POST /api/evals/:name/rescore`, `GET /api/decisions`, `POST /api/tools/:name/test`, `POST /api/workflows/:name/execute` (sync); streaming WS broadcasts on `/workflows/:name/execute` with `stream: true`, `/api/playground/chat`, AND the trace channel firehose (`trace:{executionId}`) all scrub `AxlEvent` content before send.
 
 Studio checks the flag via `runtime.isRedactEnabled(): boolean` — it does **not** reach into the config object directly, because `Readonly<AxlConfig>` is shallow and consumers could mutate the nested `trace.redact` field via sub-object access. `GET /api/health` also reports `readOnly: boolean` so clients can gate mutating UI affordances.
 
@@ -498,7 +499,7 @@ src/
     types.ts              API types, WebSocket message types
     aggregates/
       aggregate-snapshots.ts  AggregateSnapshots<State> helper (per-window state, fold, replace, broadcastTransform)
-      trace-aggregator.ts     TraceAggregator<State> — TraceEvent consumer (costs, trace-stats)
+      trace-aggregator.ts     TraceAggregator<State> — AxlEvent consumer (costs, trace-stats)
       execution-aggregator.ts ExecutionAggregator<State> — ExecutionInfo consumer (workflow-stats)
       eval-aggregator.ts      EvalAggregator<State> — EvalHistoryEntry consumer (eval-trends)
       reducers.ts             Pure reducers: reduceCost, reduceWorkflowStats, reduceTraceStats, reduceEvalTrends + enrichWorkflowStats