Skip to content

Add optional autoresearch hint model tool #65

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
0exec wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add optional autoresearch hint model tool #65

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,12 @@

All notable changes to this project will be documented in this file.

## Unreleased

### Added

- Optional `ask_autoresearch_hint` tool. When enabled in `autoresearch.config.json`, the loop can ask a configured larger pi model for bounded, side-effect-free strategy advice after stalled or failed experiment attempts.

## [1.4.0] - 2026-05-06

### Added
Expand Down
19 changes: 18 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,7 @@ pi install npm:pi-autoresearch
| `init_experiment` | One-time session config — name, metric, unit, direction |
| `run_experiment` | Runs any command, times wall-clock duration, captures output |
| `log_experiment` | Records result, auto-commits, updates widget and dashboard |
| `ask_autoresearch_hint` | *(Optional)* Ask a configured larger model for concise strategy advice when the loop is stuck |

### `/autoresearch` command

Expand Down Expand Up @@ -209,14 +210,30 @@ Create `autoresearch.config.json` in your pi session directory to customize beha
```json
{
"workingDir": "/path/to/project",
"maxIterations": 50
"maxIterations": 50,
"hints": {
"enabled": true,
"provider": "anthropic",
"model": "claude-opus-4-5",
"thinkingLevel": "high",
"maxRecentRuns": 8,
"maxCallsPerSession": 5,
"timeoutSeconds": 120
}
}
```

| Field | Type | Description |
|-------|------|-------------|
| `workingDir` | string | Override the directory for all autoresearch operations — file I/O, command execution, and git. Supports absolute or relative paths (resolved against the pi session cwd). The config file itself always stays in the session cwd. Fails if the directory doesn't exist. |
| `maxIterations` | number | Maximum experiments before auto-stopping. The agent is told to stop and won't run more experiments until a new segment is initialized. |
| `hints` | object | Optional expensive-model hint tool config. Missing or `enabled: false` means no hint model calls are made. When enabled, `provider` and `model` must match a configured pi model. |

`ask_autoresearch_hint` is a side-channel advisory tool. It never edits files,
changes the active pi model, commits, reverts, or writes `autoresearch.jsonl`.
The agent is guided to use it only after repeated discards/crashes, stalled
progress, or unclear next hypotheses, and every suggestion still has to be
validated through `run_experiment` and `log_experiment`.

### Long-running loops and context

Expand Down
Loading