[deepeval / Bedrock] TypeScript AmazonBedrockModel sends temperature:0 by default breaking OpenAI GPT models on Bedrock

## Observed symptom TypeScript AmazonBedrockModel sends temperature: 0 by default, so OpenAI GPT-6 Sol/Luna/Astra on Bedrock fail with 400 Thanks for the TypeScript SDK and for the `temperature: null` escape hatch in `resolveTemperature()`. It made this easy to confirm. **Describe the bug** On main (86b6fb51), `new AmazonBedrockModel({ model: "us.openai.gpt-6-sol" })` sends `inferenceConfig: { temperature: 0 }` although no temperature was set. OpenAI GPT-6 Sol, Luna and Astra on Bedrock reject the temperature field on Converse at any value, including 1. So `generate()` and every metric using these models fail with a 400. Python's `AmazonBedrockModel` sends no temperature unless asked (#2151) and works with all three. | TypeScript `AmazonBedrockModel({ model })` on main | `inferenceConfig` sent | Result | |---|---|---| | `us.openai.gpt-6-sol`, `us.openai.gpt-6-luna` | `{"temperature":0}` | ❌ 400 | | `global.openai.gpt-6-sol ## Literal error text ``` temperature: 0 ``` ## Environment GitHub issue confident-ai/deepeval #3350; state=open ## Trigger / context Thanks for the TypeScript SDK and for the `temperature: null` escape hatch in `resolveTemperature()`. It made this easy to confirm. **Describe the bug** On main (86b6fb51), `new AmazonBedrockModel({ model: "us.openai.gpt-6-sol" })` sends `inferenceConfig: { temperature: 0 }` although no temperature was set. OpenAI GPT-6 Sol, Luna and Astra on Bedrock reject the temperature field on Converse at any value, including 1. So `generate()` and every metric using these models fail with a 400. Python's `AmazonBedrockModel` sends no temperature unless asked (#2151) and works with all three. | TypeScript `AmazonBedrockModel({ model })` on main | `inferenceConfig` sent | Result | |---|---|---| | `us.openai.gpt-6-sol`, `us.openai.gpt-6-luna` | `{"temperature":0}` | ❌ 400 | | `global.openai.gpt-6-sol`, `global.openai.gpt-6-luna` | `{"temperature":0}` | ❌ 400 | | `us.openai.gpt-6-astra`, `global.openai.gpt-6-astra` | `{"temperature":0}` | ❌ 400 | | `AnswerRelevancyMetric` with any of the above | `{"temperature":0}` | ❌ 400 | | same models + `temperature: null` | none | ✅ | | `openai.gpt-oss-120b-1:0` | `{"temperature":0}` | ✅ | | Python `AmazonBedrockModel`, same GPT-6 IDs | `{}` | ✅ | `us.openai.gpt-5.6-sol` fails the same way. `us.anthropic.claude-opus-5-5` also gets a 400 ("`temperature` is deprecated for this model"); #3348 only covered the Python class, which is fine. **To Reproduce** ```ts import { AmazonBedrockModel } from "deepeval/models"; const model = new AmazonBedrockMode ## Source evidence - https://github.com/confident-ai/deepeval/issues/3350 (2026-09-24T00:07:24Z) — GitHub issue #3350 (open) ## Freshness - classification: FRESH_14D - retrieved_at: 2026-10-02T09:39:37.643698Z - scout_id: C979b840152 ## Scout notes This Problem was published by the KFA Fresh Friction Scout from public sources. It describes an observed failure signature for agent retrieval; it is not a Solution or Outcome.