Documentation
¶
Overview ¶
Package runner manages the agent lifecycle including Docker-based task execution, review orchestration, and the top-level poll loop that drives claiming, running, and merging tasks.
Index ¶
- func DryRun(w io.Writer, repoRoot, branch string, opts RunOptions) error
- func PostReviewAction(tasksDir, agentID string, task *queue.ClaimedTask)
- func Run(repoRoot, branch string, opts RunOptions) error
- func SelectAndLockReview(tasksDir string, idx *queueview.PollIndex) (*queue.ClaimedTask, func())
- func SelectTaskForReview(tasksDir string, idx *queueview.PollIndex) *queue.ClaimedTask
- func VerifyReviewBranch(repoRoot, tasksDir string, task *queue.ClaimedTask, agentID string) bool
- type DryRunRenderer
- func (r *DryRunRenderer) RenderAffectsConflicts(view queueview.RunnableBacklogView)
- func (r *DryRunRenderer) RenderBacklogSummary(idx *queueview.PollIndex, deferred map[string]struct{}, ...)
- func (r *DryRunRenderer) RenderDependencyResolution(promotable int)
- func (r *DryRunRenderer) RenderDependencySummary(tasksDir string, idx *queueview.PollIndex)
- func (r *DryRunRenderer) RenderExecutionOrder(runnable []*queueview.TaskSnapshot)
- func (r *DryRunRenderer) RenderQueueSummary(idx *queueview.PollIndex, subdirs []string, parseFailuresByDir map[string]int, ...)
- func (r *DryRunRenderer) RenderResolvedSettings(opts RunOptions)
- func (r *DryRunRenderer) RenderValidation(parseFailures []queueview.ParseFailure, totalTasks int)
- type RunMode
- type RunOptions
- type ToolFinding
- type ToolReport
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
func DryRun ¶
func DryRun(w io.Writer, repoRoot, branch string, opts RunOptions) error
DryRun validates the task queue setup without launching Docker containers. It runs one iteration of queue management (dependency promotion, overlap detection, manifest writing) and reports the results to w, then exits.
func PostReviewAction ¶
func PostReviewAction(tasksDir, agentID string, task *queue.ClaimedTask)
PostReviewAction is the exported entry point for the host-side review handoff after a review agent exits. It delegates to the internal postReviewAction implementation.
func Run ¶
func Run(repoRoot, branch string, opts RunOptions) error
func SelectAndLockReview ¶
func SelectAndLockReview(tasksDir string, idx *queueview.PollIndex) (*queue.ClaimedTask, func())
SelectAndLockReview is the exported entry point for selecting and locking the highest-priority review candidate. It delegates to selectAndLockReview.
func SelectTaskForReview ¶
func SelectTaskForReview(tasksDir string, idx *queueview.PollIndex) *queue.ClaimedTask
SelectTaskForReview is the exported entry point for selecting the highest-priority review candidate. It delegates to selectTaskForReview.
func VerifyReviewBranch ¶
func VerifyReviewBranch(repoRoot, tasksDir string, task *queue.ClaimedTask, agentID string) bool
VerifyReviewBranch checks whether the task branch exists in the host repo before launching a review agent. If the branch is missing it records a review-failure marker and returns false. Returns true when the branch exists and the review may proceed.
Types ¶
type DryRunRenderer ¶
DryRunRenderer formats dry-run validation output to a writer with optional color and terminal-width-aware layout.
func (*DryRunRenderer) RenderAffectsConflicts ¶
func (r *DryRunRenderer) RenderAffectsConflicts(view queueview.RunnableBacklogView)
RenderAffectsConflicts writes the === Affects Conflict Detection === section and any dependency-blocked backlog tasks.
func (*DryRunRenderer) RenderBacklogSummary ¶
func (r *DryRunRenderer) RenderBacklogSummary(idx *queueview.PollIndex, deferred map[string]struct{}, blocked map[string][]queueview.DependencyBlock)
RenderBacklogSummary writes the === Backlog Task Summary === section with compact frontmatter for every parsed backlog task.
func (*DryRunRenderer) RenderDependencyResolution ¶
func (r *DryRunRenderer) RenderDependencyResolution(promotable int)
RenderDependencyResolution writes the === Dependency Resolution === section.
func (*DryRunRenderer) RenderDependencySummary ¶
func (r *DryRunRenderer) RenderDependencySummary(tasksDir string, idx *queueview.PollIndex)
RenderDependencySummary writes the === Dependency Summary === section for waiting/ tasks, showing each dependency and its resolved queue state.
func (*DryRunRenderer) RenderExecutionOrder ¶
func (r *DryRunRenderer) RenderExecutionOrder(runnable []*queueview.TaskSnapshot)
RenderExecutionOrder writes the === Execution Order === section showing runnable backlog tasks in priority order with their priority values.
func (*DryRunRenderer) RenderQueueSummary ¶
func (r *DryRunRenderer) RenderQueueSummary(idx *queueview.PollIndex, subdirs []string, parseFailuresByDir map[string]int, deferredCount int)
RenderQueueSummary writes the === Queue Summary === section.
func (*DryRunRenderer) RenderResolvedSettings ¶
func (r *DryRunRenderer) RenderResolvedSettings(opts RunOptions)
RenderResolvedSettings writes the === Resolved Settings === section.
func (*DryRunRenderer) RenderValidation ¶
func (r *DryRunRenderer) RenderValidation(parseFailures []queueview.ParseFailure, totalTasks int)
RenderValidation writes the === Task File Validation === section.
type RunOptions ¶
type RunOptions struct {
DockerImage string
Mode RunMode
TaskModel string
ReviewModel string
ReviewSessionResumeEnabled bool
TaskReasoningEffort string
ReviewReasoningEffort string
AgentTimeout time.Duration
RetryCooldown time.Duration
Verbose bool
}
RunOptions holds configuration values for a mato run.
TaskModel, ReviewModel, TaskReasoningEffort, and ReviewReasoningEffort must already be resolved to non-empty values before calling Run or DryRun. DockerImage, AgentTimeout, RetryCooldown, and Mode may be left zero to use downstream defaults.
type ToolFinding ¶
type ToolFinding struct {
Name string
Path string // resolved path, empty if not found
Required bool
Found bool
Message string
}
ToolFinding describes a single tool or directory inspection result.
type ToolReport ¶
type ToolReport struct {
Findings []ToolFinding
}
ToolReport collects all tool inspection findings.
func InspectHostTools ¶
func InspectHostTools() ToolReport
InspectHostTools probes all host tools and directories, returning structured findings for every item regardless of success or failure. This is a parallel implementation that mirrors the checks in discoverHostTools() but collects findings instead of failing fast. discoverHostTools() is NOT modified.