Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
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
8 changes: 8 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,14 @@ All notable changes to this project will be documented in this file.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).

## [Unreleased]

### Changed
- `actual advisor` now streams its answer over Server-Sent Events instead of polling. Phase progress (fetching, interpreting, summarizing) renders to stderr while the answer is prepared, and the final answer prints to stdout. The previous client-side five-minute cap is gone, so a longer ADR-backed question runs to completion.

### Added
- `actual advisor --json` prints the answer as JSON on stdout for scripting; phase progress stays on stderr so stdout remains clean.

## [0.1.4] - 2026-03-31

### Fixed
Expand Down
22 changes: 22 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -120,6 +120,7 @@ you've written yourself.

```
actual adr-bot # analyze repo & write AI context files
actual advisor "<q>" # ask the Advisor an org-scoped architecture question
actual status # check output file state (managed markers, staleness)
actual auth # verify authentication
actual config show # view current configuration
Expand All @@ -130,6 +131,27 @@ actual models # list known model names grouped by runner
actual cache clear # clear local analysis and tailoring caches
```

## Ask the Advisor

`actual advisor` asks the Actual AI Advisor an org-scoped architecture
question and streams the answer back over Server-Sent Events. Progress steps
(fetching, interpreting, summarizing) print to stderr as the answer is
prepared; the final answer prints to stdout, so it stays pipeable. There is
no fixed time limit, so a longer ADR-backed question runs to completion.

```bash
actual login # one-time sign-in
actual advisor "Should new services use gRPC or REST?"
```

Scope the question to one connected repository, or emit the answer as JSON
for scripting:

```bash
actual advisor --repo <repo-id> "..." # scope to one repo (org-wide if omitted)
actual advisor --json "..." | jq .summary # machine-readable answer on stdout
```

## Configuration

Config lives at `~/.actualai/actual/config.yaml` and is created automatically
Expand Down
Loading
Loading