Documentation
¶
Overview ¶
Package review runs a directory of prompts as independent reviews, each on its own sidecar.
Index ¶
Constants ¶
const DefaultDir = ".chunk/reviews"
DefaultDir is where prompts are read from, relative to the project root, when no directory is given.
const DefaultTimeout = 15 * time.Minute
DefaultTimeout bounds one review. Claude explores the repo before answering, so this is minutes rather than the seconds a single API call would take.
const PoolName = "review"
PoolName is the sidecar pool name for reviews. It keys the persisted pool state in .chunk/review-pool.json, so a later run — or a later pass in the same run — picks up the same warm sidecars instead of booting new ones.
Variables ¶
var ErrClaudeMissing = errors.New("claude is not installed on the sidecar")
ErrClaudeMissing is returned when a sidecar has no claude binary.
var ErrNoPrompts = errors.New("no prompts found")
ErrNoPrompts is returned when a prompts directory holds nothing to review.
Functions ¶
func ClientExec ¶
func ClientExec(ctx context.Context, entry *sidecar.PoolEntry, script string, env map[string]string, onOutput circleci.OutputFn) (int, error)
ClientExec runs scripts through the pool entry's CircleCI client.
func PoolSize ¶
PoolSize picks how many sidecars to boot: one per prompt, capped at the requested parallelism. Booting more sidecars than prompts only bills idle machines, since each review occupies exactly one sidecar.
func WaitReady ¶
WaitReady blocks until the pool's background clone creation and sync have finished, via waitSynced (the pool's WaitSynced), and reports any member that failed.
sidecar.NewPool returns as soon as its members exist, while reused members may still be syncing in the background. Waiting here makes a failed sync surface before any review starts, rather than as one review failing partway through a pass. It holds no members while waiting: the pool reports a failed member through Acquire only once nothing is checked out.
Types ¶
type Execer ¶
type Execer func(ctx context.Context, entry *sidecar.PoolEntry, script string, env map[string]string, onOutput circleci.OutputFn) (exitCode int, err error)
Execer runs a shell script on a sidecar and streams its output.
type Options ¶
type Options struct {
APIKey string
Model string // optional; claude's default when empty
Timeout time.Duration // per review; DefaultTimeout when zero
StatusFn iostream.StatusFunc
}
Options configures one review pass.
type Prompt ¶
Prompt is one review to run. Name is the file name without its extension and identifies the review in output across passes.
func LoadPrompts ¶
LoadPrompts reads every prompt file directly inside dir, sorted by name so runs are reproducible. Subdirectories are not descended into, and files that are empty after trimming whitespace are skipped rather than run as blank reviews.
type Result ¶
type Result struct {
Prompt string
SidecarID string
Output string
Error string
Duration time.Duration
}
Result is the outcome of one prompt in one pass. Output and Error are not exclusive: a review that fails partway keeps what it produced.
func RunPass ¶
func RunPass(ctx context.Context, acquire func(context.Context) (*sidecar.PoolEntry, error), release func(*sidecar.PoolEntry), exec Execer, prompts []Prompt, opts Options) ([]Result, error)
RunPass runs every prompt once, each on a sidecar checked out with acquire and returned with release (the pool's Acquire and Release), and returns results in prompt order for every prompt that started. Per-prompt failures are recorded in Result.Error; the returned error is for failures that stop the pass itself.
A missing claude binary stops the pass rather than being recorded per prompt: every sidecar in a pool comes from one image, so it would fail every review the same way.
Source Files