feat(agents): enable conservative retries by default for transient errors

[MarioCadenas]

What

Agents previously disabled retries entirely — agentStreamDefaults set retry: { enabled: false }. A single transient serving error (5xx, 429, connection reset) would fail the whole turn.

This enables a conservative default that reuses the existing RetryInterceptor (exponential backoff with full jitter, only retries transient/retryable errors):

retry: { enabled: true, attempts: 2, initialDelay: 500, maxDelay: 4_000 }

• Old default: retries off — any transient blip failed the turn.
• New default: at most one extra attempt, 500ms→4s jittered backoff. Non-retryable errors (4xx, AppKitError with isRetryable=false) are still never retried — see isRetryableError in interceptors/retry.ts.

No new retry logic was added; only the default config value changed.

Streaming / non-idempotency safety (the scope applied)

The agents plugin consumes retry in exactly one place: the streaming /chat path via executeStream (agents.ts:1162). This change is streaming-replay-safe by construction, not by configuration:

• In executeStream, the interceptor chain wraps wrappedFn = async () => fn(signal), where fn is the async generator function for the turn.
• Calling a generator function returns the generator object synchronously without running its body. So wrappedFn resolves immediately and the RetryInterceptor sees success on attempt 1.
• Token emission and tool dispatch happen later, during yield* iteration — which runs outside the interceptor chain.
• Therefore a transient error thrown after the first streamed event surfaces during iteration and is never seen by the retry loop. There is no path by which retry can re-emit tokens or re-run a tool side-effect (no double-charge / duplicate writes).
• The only thing retried is a transient failure during generator setup, before any output — which is safe and idempotent.

The non-streaming /invocations and /responses path (_runAgentNonStreaming) does not route through execute()/executeStream() at all, so this default does not affect it.

Tests

Added packages/appkit/src/plugins/agents/tests/defaults.test.ts:

• asserts the conservative default values (enabled, attempts === 2, bounded backoff caps).
• proves no mid-stream replay: drives the real RetryInterceptor exactly as executeStream does, throws a 5xx after the first yielded token, and asserts the generator body ran once and the tool side-effect fired once (no replay).
• proves a transient error during generator setup (before output) is retried.

Verification

• pnpm --filter=@databricks/appkit typecheck — clean.
• agents suite: 120 passed; retry.test.ts: 19 passed; new defaults.test.ts: 3 passed.
• biome check on changed files — no fixes/errors.

This pull request and its description were written by Isaac.

[github-actions]

📦 Bundle size report

Compared against bundle-size-baseline.json (main).

@databricks/appkit

npm tarball (packed): 659 KB (+460 B) — gzipped download (dist + bin; excludes release-only docs/NOTICE).

dist	raw	gzip
JS (runtime)	686 KB (+60 B)	240 KB (+40 B)
Type declarations	268 KB	91 KB
Source maps	1.3 MB (+973 B)	446 KB (+519 B)
Other	11 KB	3.7 KB
Total	2.3 MB (+1.0 KB)	780 KB (+559 B)

Per-entry composition (own code — deps external (as shipped))

Entry	Initial (gz)	Lazy (gz)	Total (gz)	node_modules (min)	Own code (min)
.	74 KB	2.5 KB	76 KB	external	243 KB
./beta	39 KB (+17 B)	231 B	39 KB (+17 B)	external	117 KB (+41 B)
./type-generator	18 KB	0 B	18 KB	external	53 KB

Chunks:

Entry	Chunk	Load	Size (gz)
.	index.js	initial	70 KB
.	utils.js	initial	4.0 KB
.	remote-tunnel-manager.js	lazy	2.5 KB
./beta	beta.js	initial	30 KB
./beta	databricks.js	initial	5.7 KB
./beta	service-context.js	initial	3.1 KB
./beta	client-options.js	initial	220 B
./beta	databricks.js	lazy	128 B
./beta	index.js	lazy	103 B
./type-generator	index.js	initial	18 KB

@databricks/appkit-ui

npm tarball (packed): 298 KB — gzipped download (dist + bin; excludes release-only docs/NOTICE).

dist	raw	gzip
JS (runtime)	354 KB	117 KB
Type declarations	204 KB	73 KB
Source maps	676 KB	220 KB
CSS	16 KB	3.3 KB
Total	1.2 MB	413 KB

Per-entry composition (consumer bundle — deps bundled, peerDeps external)

Entry	Initial (gz)	Lazy (gz)	Total (gz)	node_modules (min)	Own code (min)
./js	4.2 KB	49 KB	54 KB	208 KB	11 KB
./js/beta	20 B	0 B	20 B	0 B	0 B
./react	429 KB	49 KB	477 KB	1.3 MB	166 KB
./react/beta	20 B	0 B	20 B	0 B	0 B

Chunks:

Entry	Chunk	Load	Size (gz)
./js	index.js	initial	4.1 KB
./js	chunk	initial	120 B
./js	apache-arrow	lazy	49 KB
./js/beta	beta.js	initial	20 B
./react	index.js	initial	427 KB
./react	tslib	initial	2.1 KB
./react	apache-arrow	lazy	49 KB
./react/beta	beta.js	initial	20 B