feat(agents): forward generation params (temperature/top_p/stop/...) to the serving adapter

[MarioCadenas]

The gap

The Databricks agent adapter (DatabricksAdapter) sent only max_tokens to the OpenAI-compatible serving endpoint. App engineers had no way to tune generation (temperature, nucleus sampling, stop sequences, penalties) — a basic parity gap vs. the Vercel AI SDK / LangChain.

What changed

Forward the standard OpenAI-compatible generation params into the serving request body:

• temperature
• top_p
• stop (string or string[])
• frequency_penalty
• presence_penalty

Where they're declared (all optional / opt-in)

• GenerationParams interface in packages/appkit/src/agents/databricks.ts, accepted on every DatabricksAdapter options shape (raw fetch, stream-body, fromServingEndpoint, fromModelServing) and exported from @databricks/appkit/beta.
• AgentDefinition.generationParams and RegisteredAgent.generationParams in packages/appkit/src/core/agent/types.ts, wired through packages/appkit/src/plugins/agents/agents.ts into the adapter options (same path as maxTokens, only applied when AppKit builds the adapter from a string/omitted model).
• Markdown frontmatter generationParams: in packages/appkit/src/core/agent/load-agents.ts, parsed defensively (only known keys with the expected wire types are picked).

Names match the serving API wire keys. Only keys that are set are written to the request body; undefined keys are omitted so the endpoint applies its own defaults. No range validation is added — the endpoint validates.

Verification

• pnpm --filter=@databricks/appkit typecheck — clean.
• vitest run --project appkit for the adapter, core agent, and agents plugin suites — 348 tests pass, including two new adapter tests asserting (a) set params are forwarded and (b) unset params are omitted from the body.
• biome check on the edited files introduces no new warnings (the two agents.ts warnings are pre-existing on main).

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): 661 KB (+2.4 KB) — gzipped download (dist + bin; excludes release-only docs/NOTICE).

dist	raw	gzip
JS (runtime)	688 KB (+1.6 KB)	240 KB (+506 B)
Type declarations	269 KB (+1.6 KB)	91 KB (+517 B)
Source maps	1.3 MB (+5.1 KB)	447 KB (+1.5 KB)
Other	11 KB	3.7 KB
Total	2.3 MB (+8.3 KB)	782 KB (+2.5 KB)

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 (+295 B)	231 B	39 KB (+295 B)	external	118 KB (+964 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	5.8 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