feat(stage): honor per-stage reasoning effort across native harnesses

This commit is contained in:
2026-10-20 23:51:14 +01:00
parent 9ce2c5d143
commit 724de27561
11 changed files with 233 additions and 20 deletions
+38
View File
@@ -1,5 +1,43 @@
# Harnesses and runner-owned control
## Reasoning effort (thinking level)
Add an optional setting to the model stage's existing `configs` block:
````markdown
```configs
provider=openai
model=gpt-5.2
reasoning_effort=high
```
````
Use your actual configured provider/model IDs. Each stage chooses its own level;
leaving it out, or using `default`, preserves the model/harness default.
| Setting | Behavior |
| --- | --- |
| `none` (alias `off`) | Disable reasoning, when supported |
| `minimal`, `low`, `medium`, `high`, `xhigh`, `max` | Select that native effort level, when supported |
| omitted / `default` | Leave existing defaults unchanged |
OpenCode V2 passes this as the selected model's named **variant**, for both
text-only and tool-using stages. Variant availability is model-specific; an
unavailable level is rejected, not silently replaced. See
[OpenCode variants](https://opencode.ai/v2/docs/models#variants).
Pi uses its native **thinking level**, mapping `none` to `off`, and verifies that
the selected model actually applied it before sending the task. Unsupported or
clamped levels fail clearly; availability also depends on the installed Pi
version. OpenCode V1 cannot apply this setting and rejects explicit effort.
This is a native runtime option, not a prompt instruction or token limit. Higher
effort can increase latency and cost; keep `budget_tokens`, `budget_usd`, and
provider spending limits separate. Existing definitions, defaults and published
versions are never rewritten. Editing the setting requires publishing a new
pipeline version as usual.
## Harness defaults
Configure two independent model defaults:
```sh