remove hardcoded agent temp

[filip-michalsky]

why

Reasoning models (e.g. openai/gpt-5-mini) emit AI SDK Warning: The "temperature" setting is not supported by this model whenever the v3 agent
runs against them, because V3AgentHandler hardcoded temperature: 1 on every generateText/streamText call. There was no constructor or
agent-config option to override it, so users running reasoning models with experimental: true had no way to silence the warning.

what changed

• Removed the hardcoded temperature: 1 from both the non-streaming and streaming agent paths in
  packages/core/lib/v3/handlers/v3AgentHandler.ts.
• Agent calls now omit temperature entirely, so the AI SDK no longer flags it as user-set on models that don't accept it. Models that do accept
  temperature still default to the AI SDK provider's own default.
• Added unit coverage in packages/core/tests/unit/agent-temperature.test.ts asserting neither code path passes a temperature to the LLM
  client.
• Added a patch changeset (.changeset/remove-agent-temperature-default.md).

test plan

• pnpm --filter @browserbasehq/stagehand test agent-temperature — new unit tests pass
• Existing v3 agent unit suite stays green
• Manual: agent.execute(...) against openai/gpt-5-mini with experimental: true — confirm no "temperature" setting is not supported
  warning in stderr
• Manual: same call against a non-reasoning model (e.g. openai/gpt-4.1-mini) — confirm agent still completes a multi-step task end-to-end
• Manual: hybrid-mode agent run on a reasoning model — verify streaming path is also clean

[changeset-bot]

🦋 Changeset detected

Latest commit: a27102b

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 4 packages

Name	Type
@browserbasehq/stagehand	Patch
@browserbasehq/stagehand-evals	Patch
@browserbasehq/stagehand-server-v3	Patch
@browserbasehq/stagehand-server-v4	Patch

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR

[github-actions]

✱ Stainless preview builds

No changes were made to the SDKs.

---

This comment is auto-generated by GitHub Actions and is automatically kept up to date as you push.
If you push custom code to the preview branch, re-run this workflow to update the comment.
Last updated: 2026-04-30 20:28:44 UTC

[cubic-dev-ai]

No issues found across 3 files

Confidence score: 5/5

• Automated review surfaced no issues in the provided summaries.
• No files require special attention.

Architecture diagram

sequenceDiagram
    participant App as Client Application
    participant Agent as V3AgentHandler
    participant SDK as LLMClient (AI SDK)
    participant Model as LLM Provider (e.g. OpenAI)

    App->>Agent: execute(instruction) or stream(...)
    
    Note over Agent: Prepare tools, messages,<br/>and stop conditions

    alt Non-Streaming Path
        Agent->>SDK: CHANGED: generateText(options)
        Note right of Agent: NEW: temperature is omitted<br/>(previously hardcoded to 1)
        SDK->>Model: Request without "temperature" field
    else Streaming Path
        Agent->>SDK: CHANGED: streamText(options)
        Note right of Agent: NEW: temperature is omitted
        SDK->>Model: Stream request without "temperature" field
    end

    alt Model is Reasoning Model (e.g. gpt-5-mini)
        Model-->>SDK: Processes request successfully
        Note over Model: No AI SDK warning emitted<br/>because temperature was not set
    else Model is Standard Model (e.g. gpt-4o)
        Model-->>SDK: Processes request successfully
        Note over Model: Uses provider's internal<br/>default temperature
    end

    SDK-->>Agent: LLM Result/Stream
    Agent-->>App: Task Result / Execution Logs

Loading

[filip-michalsky]

That failing auto-captcha test is going to get removed.