… chat spans (#23316)

`chats.create()` takes a `config` (temperature, topP, topK,
maxOutputTokens, frequencyPenalty, presencePenalty, tools,
systemInstruction) that `@google/genai` reuses for every
`chat.sendMessage()` and `chat.sendMessageStream()` call on that chat.
#19990 removed the `chats.create()` span, which was the only span
reporting those values, and nothing took over. Chat spans have carried
model and token counts but no request config since then.

Both google-genai instrumentation paths are fixed:

- `instrumentGoogleGenAIClient`, the client proxy, used by
`@sentry/cloudflare` and `@sentry/vercel-edge` and available for manual
wrapping.
- `googleGenAIIntegration`, the diagnostics-channel integration, which
is the default for Node, Bun, Deno, Astro, AWS Lambda and Google Cloud
Functions.

Only the first path was in the original report, but both build their
attributes from the per-message arguments alone, so both lost the same
data.

**Decisions**

**The config is read from the chat instance, not captured at create
time.** `@google/genai` stores `config` as a plain property on the
`Chat` object, and both paths already hold that object: the proxy passes
it as the instrumented method's `context`, and the channel path receives
it as `data.self`. `extractModel()` already recovers the model the same
way. Carrying the `chats.create()` arguments forward instead would have
meant threading state through `createDeepProxy`, which fixes only the
proxy path and moves that function away from its `openai` and
`anthropic-ai` counterparts that #19990 deliberately converged. The cost
is a dependency on an internal field name, which this file already
accepts for `model` / `modelVersion`.

**A per-message config replaces the chat config, it does not merge into
it.** The SDK resolves the request as `params.config ?? chat.config`, so
a message that carries its own config sends only that config. The span
mirrors that. Merging key by key would report a create-time
`maxOutputTokens` alongside a per-message `temperature` and describe a
request that was never sent.

**The chat `history` stays off the message spans.** The SDK does send
it, folded into `contents`, and the instance carries the whole
transcript, but repeating every past turn on every message span
duplicates what earlier spans already reported and grows without bound.
`gen_ai.request.messages` keeps just the message being sent.

**Non-chat calls are unaffected.** `models.generateContent` and
`models.embedContent` have no chat instance, so they resolve their
config from their own arguments exactly as before.

Fixes #20086

AI assistance (Claude, Anthropic) was used in developing this change.
The design, review and verification were done by the author.

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: isaacs <i@izs.me>