> ## Documentation Index
> Fetch the complete documentation index at: https://docs.deeda.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Thinking & Reasoning

> Buy more reasoning when the task is hard: thinking budgets per provider, in one schema.

**ELI5:** every provider sells "think harder" under a different name
(extended thinking, reasoning effort, thinking level). deeda gives you one
workflow field plus per-provider knobs; the harness maps them.

## The portable field

```yaml theme={null}
agent:
  thinking:
    type: enabled        # enabled | disabled | adaptive
    budget_tokens: 16000 # or "{{thinking_budget}}" template
```

## Per-provider mapping

| Provider/runtime                                                | Knob (under `harness_config.sdk_settings.<provider>`)                                | Values                                                                             |
| --------------------------------------------------------------- | ------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------- |
| `anthropic-agent-sdk`                                           | `thinking_type`, `thinking_budget_tokens`                                            | enabled/disabled/adaptive + token cap; interleaved & adaptive thinking implemented |
| `openai-codex-sdk`, `openai-agents-sdk`, `openai-responses-api` | `reasoning_effort`                                                                   | model-dependent (o-series / GPT-5 class)                                           |
| `gemini-antigravity-cli`                                        | `antigravity_thinking_level`                                                         | `MINIMAL` \| `LOW` \| `MEDIUM` \| `HIGH`                                           |
| `gemini-genai-sdk`                                              | thinking on/off/dynamic is implemented at the capability level; no extra knob needed | —                                                                                  |
| `local-llm`, `local-voice`                                      | none — local models expose no thinking control                                       | —                                                                                  |

Caveats worth knowing: Anthropic *summarized* thinking is model-dependent
(4-series vendor default, no deeda selector); OpenAI `reasoning_effort` is
rejected by non-reasoning models — pin a supporting `model`; Gemini
deep-research is policy-blocked (long-running paid surface).

## Example: pay for reasoning only on the hard stage

```yaml theme={null}
state_machine:
  stage_order: [scan, deep_fix]
  states:
    scan:
      agent:
        thinking: { type: disabled }
    deep_fix:
      agent:
        thinking: { type: enabled, budget_tokens: 24000 }
```

## When to use

| Task                             | Setting                                |
| -------------------------------- | -------------------------------------- |
| Bulk/mechanical edits, summaries | `disabled` — thinking is wasted spend  |
| Debugging, architecture, proofs  | `enabled` with 16–32k budget           |
| Mixed/unknown difficulty         | `adaptive` (Anthropic) — model decides |

## See also

* [Workflow Schema](/harness/workflow-schema#agent) — field shapes
* Provider pages for per-row status: [Anthropic](/harness/providers/anthropic#extended-thinking), [Gemini](/harness/providers/gemini), [OpenAI](/harness/providers/openai)