a6aff47117
A new registered stage type `human` (internal/stage/human.go) has no model,
agent, tools or configs: its required `prompt` block carries the operator
instructions and its non-error edges are the selectable options. It parses,
validates, renders, exports and imports like every other type (no parser
special-case, no config keys).
At runtime the runner parks the run instead of executing: the step and the run
persist `waiting` with self-contained {prompt, options} evidence, and the run
returns without starting later stages, capturing file diffs, scanning artifacts,
holding a goroutine/timer or applying a stage timeout. The wait is durable: a
restart leaves the waiting rows untouched (RecoverRuns excludes them) and a
rebuilt runtime over the same database still accepts the decision.
`pipelines decide <run-id> [stage] --option KEY [--feedback TEXT] [--json]` and
the TUI `c` picker resolve the decision from the pinned graph in one store
transaction, record the choice and feedback as the step's evidence and resume
along edges[KEY]. An unknown option is refused with the valid list, a stage that
is not waiting is refused, and a repeated decision for an already-decided visit
does not double-apply. Cancel and retry keep working while waiting and after a
decision; a human stage is never killed by a stage timeout or max_visits, and a
`notify` policy can fire an `on=waiting` event.
Docs: the authoring skill references (format.md, operations.md), docs/cli.md and
README describe the stage, the command and the TUI picker. Tests cover stage
validation, the parsing round-trip, the store transitions, a websocket wait/decide
integration, cancel/retry, waiting notifications and a persistence-layer rebuild
(second Open + newRunner over one database, no process restart).
211 lines
7.9 KiB
Go
211 lines
7.9 KiB
Go
package protocol
|
|
|
|
import "strings"
|
|
|
|
const (
|
|
RunPipeline = "run_pipeline"
|
|
RunStarted = "run_started"
|
|
ListRuns = "list_runs"
|
|
Runs = "runs"
|
|
GetRun = "get_run"
|
|
Run = "run"
|
|
CancelRun = "cancel_run"
|
|
RetryRun = "retry_run"
|
|
DecideRun = "decide_run"
|
|
SetRunTitle = "set_run_title"
|
|
GetRunEvidence = "get_run_evidence"
|
|
RunEvidence = "run_evidence"
|
|
)
|
|
|
|
// Waiting statuses. A human stage pauses its run without a live goroutine, so
|
|
// the run and its step persist these statuses and the decision path resumes
|
|
// them. Store, server, CLI and TUI read the one pair below, never a literal.
|
|
const (
|
|
RunStatusWaiting = "waiting"
|
|
RunStatusRunning = "running"
|
|
StepStatusWaiting = "waiting"
|
|
// NotifyWaiting is the notification event a human stage emits when it parks
|
|
// the run. It is the same value the `on=` policy accepts.
|
|
NotifyWaiting = "waiting"
|
|
)
|
|
|
|
// Waiting evidence keys. A human stage records its operator instructions and
|
|
// its ordered selectable options in the step output, so inspect and the TUI are
|
|
// self-contained without re-reading the pinned graph.
|
|
const (
|
|
WaitingPromptKey = "prompt"
|
|
WaitingOptionsKey = "options"
|
|
)
|
|
|
|
// NewWaitingEvidence builds the self-contained evidence a human stage persists
|
|
// at wait time: the operator instructions and the ordered options to choose.
|
|
func NewWaitingEvidence(prompt string, options []string) map[string]any {
|
|
ordered := make([]any, len(options))
|
|
for i, option := range options {
|
|
ordered[i] = option
|
|
}
|
|
return map[string]any{WaitingPromptKey: prompt, WaitingOptionsKey: ordered}
|
|
}
|
|
|
|
// WaitingPrompt reads the recorded operator instructions from a waiting step's
|
|
// output, or "" when none were recorded.
|
|
func WaitingPrompt(output map[string]any) string {
|
|
prompt, _ := output[WaitingPromptKey].(string)
|
|
return prompt
|
|
}
|
|
|
|
// WaitingOptions reads the recorded selectable options from a waiting step's
|
|
// output, accepting the string and generic forms JSON decoding produces.
|
|
func WaitingOptions(output map[string]any) []string {
|
|
switch options := output[WaitingOptionsKey].(type) {
|
|
case []string:
|
|
return options
|
|
case []any:
|
|
result := make([]string, 0, len(options))
|
|
for _, option := range options {
|
|
if text, ok := option.(string); ok {
|
|
result = append(result, text)
|
|
}
|
|
}
|
|
return result
|
|
}
|
|
return nil
|
|
}
|
|
|
|
type SessionEvidence struct {
|
|
Sequence int `json:"sequence"`
|
|
SessionID string `json:"session_id"`
|
|
Backend string `json:"backend"`
|
|
Directory string `json:"directory"`
|
|
Data string `json:"data,omitempty"`
|
|
Diagnostic string `json:"diagnostic,omitempty"`
|
|
}
|
|
|
|
type RunSummary struct {
|
|
ID int64 `json:"id"`
|
|
PipelineID int64 `json:"pipeline_id"`
|
|
Name string `json:"name"`
|
|
// Title is the operator-facing, bounded single-line description of what the
|
|
// run is for, generated from its prompt. It is never empty for a new run;
|
|
// historical rows predating the title column may omit it.
|
|
Title string `json:"title,omitempty"`
|
|
Version int `json:"version"`
|
|
ContentHash string `json:"content_hash"`
|
|
Status string `json:"status"`
|
|
Executing bool `json:"executing"`
|
|
Outcome string `json:"outcome"`
|
|
CurrentStage string `json:"current_stage"`
|
|
Workspace string `json:"workspace,omitempty"`
|
|
CreatedAt string `json:"created_at"`
|
|
FinishedAt string `json:"finished_at"`
|
|
Diagnostic string `json:"diagnostic"`
|
|
ResultPreview string `json:"result_preview,omitempty"`
|
|
CompletedSteps int `json:"completed_steps"`
|
|
}
|
|
|
|
// Label is the operator-facing name of a run: the generated Title when the
|
|
// server stored one, otherwise the pipeline Name (historical rows predate
|
|
// titles). It is the single definition shared by the CLI and TUI.
|
|
func (r RunSummary) Label() string {
|
|
if title := strings.TrimSpace(r.Title); title != "" {
|
|
return title
|
|
}
|
|
return r.Name
|
|
}
|
|
|
|
type RunStep struct {
|
|
Control *ControlEvidence `json:"control,omitempty"`
|
|
FileChanges *StageFileChanges `json:"file_changes,omitempty"`
|
|
Verdict *StageVerdict `json:"verdict,omitempty"`
|
|
Notifications []NotificationReceipt `json:"notifications,omitempty"`
|
|
Artifacts []StageArtifact `json:"artifacts,omitempty"`
|
|
Sequence int `json:"sequence"`
|
|
Stage string `json:"stage"`
|
|
Status string `json:"status"`
|
|
Outcome string `json:"outcome"`
|
|
Target string `json:"target"`
|
|
Input map[string]any `json:"input"`
|
|
Output map[string]any `json:"output"`
|
|
Diagnostic string `json:"diagnostic"`
|
|
SessionID string `json:"session_id"`
|
|
AgentActive bool `json:"agent_active"`
|
|
Transcript string `json:"transcript"`
|
|
// ArtifactsSkipped and ArtifactsTruncated count files excluded from the
|
|
// bounded per-step scan (over the file/size cap) and by the total budget.
|
|
ArtifactsSkipped int `json:"artifacts_skipped,omitempty"`
|
|
ArtifactsTruncated int `json:"artifacts_truncated,omitempty"`
|
|
StartedAt string `json:"started_at"`
|
|
FinishedAt string `json:"finished_at"`
|
|
}
|
|
|
|
// StageArtifact is one file a stage left in its artifacts directory. It is
|
|
// observed server-side evidence, not a model's claim. An empty Artifacts slice
|
|
// means no files were recorded (including historical steps).
|
|
type StageArtifact struct {
|
|
Name string `json:"name"`
|
|
SizeBytes int64 `json:"size_bytes"`
|
|
ContentType string `json:"content_type"`
|
|
URL string `json:"url"`
|
|
}
|
|
|
|
type MemoryRead struct {
|
|
Source string `json:"source"`
|
|
Sequence int `json:"sequence"` // zero denotes original run input
|
|
}
|
|
|
|
type ControlEvidence struct {
|
|
Visit int `json:"visit"`
|
|
MaxVisits int `json:"max_visits"`
|
|
LimitReached bool `json:"limit_reached,omitempty"`
|
|
ModelTarget string `json:"model_target,omitempty"`
|
|
Memory map[string]MemoryRead `json:"memory,omitempty"`
|
|
}
|
|
|
|
// StageFileChanges is observed workspace evidence, not a model's claim of authorship.
|
|
// Nil means no capture was retained (including historical steps).
|
|
type StageFileChanges struct {
|
|
Omitted int `json:"omitted,omitempty"`
|
|
Scope string `json:"scope,omitempty"`
|
|
Status string `json:"status"` // complete, partial, unavailable
|
|
Files []FileChange `json:"files"`
|
|
Skipped int `json:"skipped"`
|
|
Diagnostic string `json:"diagnostic,omitempty"`
|
|
}
|
|
|
|
type FileChange struct {
|
|
Path string `json:"path"`
|
|
Kind string `json:"kind"` // added, modified, deleted
|
|
Patch string `json:"patch,omitempty"`
|
|
Binary bool `json:"binary,omitempty"`
|
|
Truncated bool `json:"truncated,omitempty"`
|
|
BeforeMode string `json:"before_mode,omitempty"`
|
|
AfterMode string `json:"after_mode,omitempty"`
|
|
}
|
|
|
|
type NotificationReceipt struct {
|
|
Destination string `json:"destination"`
|
|
Status string `json:"status"`
|
|
Filename string `json:"filename,omitempty"`
|
|
MessageID string `json:"message_id,omitempty"`
|
|
AttachmentURL string `json:"attachment_url,omitempty"`
|
|
Diagnostic string `json:"diagnostic,omitempty"`
|
|
}
|
|
|
|
type RunDetail struct {
|
|
RunSummary
|
|
Graph Graph `json:"graph"`
|
|
RetryOf int64 `json:"retry_of,omitempty"`
|
|
Workspace string `json:"workspace"`
|
|
AllowTools bool `json:"allow_tools"`
|
|
WritePaths []string `json:"write_paths"`
|
|
Input map[string]any `json:"input"`
|
|
Output map[string]any `json:"output"`
|
|
Steps []RunStep `json:"steps"`
|
|
// TitleSource is "model" when Title came from the shared summariser or
|
|
// "fallback" when it was derived from the prompt; TitleModel names the model
|
|
// that produced a model title. They are retained so a diagnosis can tell the
|
|
// two apart and see which model was used.
|
|
TitleSource string `json:"title_source,omitempty"`
|
|
TitleModel string `json:"title_model,omitempty"`
|
|
}
|