Files
pipelines/internal/pipeline/runs.go
T
alan 36fad7d130 Merge lane-go: keep the lane's reviewed work
Combines lane-go's typed omni search, launch-time model overrides, TUI
artifacts view, run-state websocket push, and the "reflect the change where
it belongs" committer rule with the Templates gallery, chat/omni-search and
other reviewed work already on main. The 12 files both sides touched keep
both intents composed rather than dropping either side: the omni search keeps
the typed search contract (CLI `pipelines search` and the TUI popup with type
badges and marked snippets) alongside the run-list quick filter; cli.md and
ui-ux-review.md document both the search rework and the artifacts view;
orchestration.md, harnesses.md and operations.md keep the model-override and
reflect-where-it-belongs guidance; and the protocol/CLI/server/TUI code keeps
the new search, run-event, override and artifacts paths alongside the existing
run, title and help surfaces.

Checks before committing:
- go build ./...  -- pass
- go vet ./...  -- pass
- go test -count=1 ./internal/... ./cmd/...  -- all pass

Doc check before committing: nothing needs updating. The lane's own docs and
references (docs/cli.md, docs/ui-ux-review.md, and the orchestration,
harnesses and operations skill references) already carry the new features.
format.md and the packaged templates already describe the line-oriented result
format and the human decision stage from the earlier lane-go merge. The root
README already describes the omni search popup. Model overrides, the search
command, run events and the artifacts view are runtime/CLI/TUI surfaces that
cli.md documents; no template, README or topic-doc edit is required by this
merge.
2026-10-17 02:04:58 +01:00

835 lines
35 KiB
Go

package pipeline
import (
"bytes"
"context"
"database/sql"
"encoding/json"
"fmt"
"strings"
"git.a-wan.net/alan/pipelines/internal/protocol"
"git.a-wan.net/alan/pipelines/internal/stage"
"git.a-wan.net/alan/pipelines/internal/summarise"
)
func (s *Store) initRuns() error {
_, err := s.db.Exec(`CREATE TABLE IF NOT EXISTS pipeline_runs (
id INTEGER PRIMARY KEY, pipeline_id INTEGER NOT NULL, version INTEGER NOT NULL,
request_key TEXT NOT NULL UNIQUE, workspace TEXT NOT NULL, allow_tools INTEGER NOT NULL,
title TEXT NOT NULL DEFAULT '', title_source TEXT NOT NULL DEFAULT '', title_model TEXT NOT NULL DEFAULT '',
model TEXT NOT NULL DEFAULT '', stage_models TEXT NOT NULL DEFAULT '{}',
write_paths TEXT NOT NULL, input_json TEXT NOT NULL, output_json TEXT NOT NULL DEFAULT '{}',
status TEXT NOT NULL DEFAULT 'queued', outcome TEXT NOT NULL DEFAULT '', current_stage TEXT NOT NULL DEFAULT '',
diagnostic TEXT NOT NULL DEFAULT '', created_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP, finished_at TEXT,
FOREIGN KEY(pipeline_id,version) REFERENCES pipeline_versions(pipeline_id,version));
CREATE TABLE IF NOT EXISTS run_steps (
run_id INTEGER NOT NULL REFERENCES pipeline_runs(id), sequence INTEGER NOT NULL, stage_key TEXT NOT NULL,
status TEXT NOT NULL DEFAULT 'running', outcome TEXT NOT NULL DEFAULT '', target TEXT NOT NULL DEFAULT '',
input_json TEXT NOT NULL, output_json TEXT NOT NULL DEFAULT '{}', diagnostic TEXT NOT NULL DEFAULT '',
provider TEXT NOT NULL DEFAULT '', model TEXT NOT NULL DEFAULT '',
session_id TEXT NOT NULL DEFAULT '', agent_active INTEGER NOT NULL DEFAULT 0, transcript TEXT NOT NULL DEFAULT '',
started_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP, finished_at TEXT, PRIMARY KEY(run_id,sequence));
CREATE INDEX IF NOT EXISTS run_latest ON pipeline_runs(id DESC);
CREATE INDEX IF NOT EXISTS run_steps_session ON run_steps(session_id);
CREATE TABLE IF NOT EXISTS step_notifications (
run_id INTEGER NOT NULL, sequence INTEGER NOT NULL, receipts_json TEXT NOT NULL,
PRIMARY KEY(run_id,sequence), FOREIGN KEY(run_id,sequence) REFERENCES run_steps(run_id,sequence));
CREATE TABLE IF NOT EXISTS step_file_changes (
run_id INTEGER NOT NULL, sequence INTEGER NOT NULL, changes_json TEXT NOT NULL,
PRIMARY KEY(run_id,sequence), FOREIGN KEY(run_id,sequence) REFERENCES run_steps(run_id,sequence));
CREATE TABLE IF NOT EXISTS step_control (
run_id INTEGER NOT NULL, sequence INTEGER NOT NULL, evidence_json TEXT NOT NULL,
PRIMARY KEY(run_id,sequence), FOREIGN KEY(run_id,sequence) REFERENCES run_steps(run_id,sequence));
CREATE TABLE IF NOT EXISTS step_artifacts (
run_id INTEGER NOT NULL, sequence INTEGER NOT NULL, artifacts_json TEXT NOT NULL,
PRIMARY KEY(run_id,sequence), FOREIGN KEY(run_id,sequence) REFERENCES run_steps(run_id,sequence));
CREATE TABLE IF NOT EXISTS step_verdicts (
run_id INTEGER NOT NULL, sequence INTEGER NOT NULL, verdict_json TEXT NOT NULL,
PRIMARY KEY(run_id,sequence), FOREIGN KEY(run_id,sequence) REFERENCES run_steps(run_id,sequence));
CREATE TABLE IF NOT EXISTS run_session_owners (
run_id INTEGER NOT NULL, sequence INTEGER NOT NULL, backend TEXT NOT NULL, reference TEXT NOT NULL DEFAULT '',
PRIMARY KEY(run_id,sequence), FOREIGN KEY(run_id,sequence) REFERENCES run_steps(run_id,sequence));
CREATE TABLE IF NOT EXISTS run_retries (
run_id INTEGER PRIMARY KEY REFERENCES pipeline_runs(id), original_run_id INTEGER NOT NULL REFERENCES pipeline_runs(id));`)
if err != nil {
return err
}
if err := s.migrateRunTitles(); err != nil {
return err
}
return s.migrateRunModels()
}
// migrateRunModels adds the launch-time model-override columns to a database
// created before per-run overrides existed. Each column is added only when
// missing, so an upgrade is idempotent across repeated Open calls and existing
// rows keep their defaults (no model override, no recorded step model).
func (s *Store) migrateRunModels() error {
for _, column := range [][3]string{
{"pipeline_runs", "model", "TEXT NOT NULL DEFAULT ''"},
{"pipeline_runs", "stage_models", "TEXT NOT NULL DEFAULT '{}'"},
{"run_steps", "provider", "TEXT NOT NULL DEFAULT ''"},
{"run_steps", "model", "TEXT NOT NULL DEFAULT ''"},
} {
if err := s.addColumnIfMissing(column[0], column[1], column[2]); err != nil {
return err
}
}
return nil
}
// migrateRunTitles adds the title columns to a database created before run
// titles existed. Adding a column with a default leaves every existing row valid
// and untouched, so old runs still list.
func (s *Store) migrateRunTitles() error {
for _, column := range [][2]string{
{"title", "TEXT NOT NULL DEFAULT ''"},
{"title_source", "TEXT NOT NULL DEFAULT ''"},
{"title_model", "TEXT NOT NULL DEFAULT ''"},
} {
if err := s.addColumnIfMissing("pipeline_runs", column[0], column[1]); err != nil {
return err
}
}
return nil
}
// addColumnIfMissing adds a column only when the table predates it, making an
// upgrade idempotent across repeated Open calls without rewriting history.
func (s *Store) addColumnIfMissing(table, column, definition string) error {
rows, err := s.db.Query("PRAGMA table_info(" + table + ")")
if err != nil {
return err
}
defer rows.Close()
for rows.Next() {
var cid, notnull, pk int
var name, ctype string
var dflt sql.NullString
if err := rows.Scan(&cid, &name, &ctype, &notnull, &dflt, &pk); err != nil {
return err
}
if name == column {
return nil
}
}
if err := rows.Err(); err != nil {
return err
}
_, err = s.db.Exec("ALTER TABLE " + table + " ADD COLUMN " + column + " " + definition)
return err
}
// RunOverrides are the launch-time model overrides recorded for a run:
// Model applies to every model stage and StageModels overrides individual model
// stages by key (per-stage wins over whole-run). They are recorded so the run
// stays reproducible without touching the pinned pipeline version.
type RunOverrides struct {
Model string
StageModels map[string]string
}
// CreateRun inserts a run and derives its title from the prompt. It is the entry
// point for callers with no generated title; the derived fallback is always
// non-empty and never calls a model.
func (s *Store) CreateRun(ctx context.Context, d *protocol.PipelineDetail, key, workspace string, tools bool, paths []string, input map[string]any, retryOf ...int64) (int64, bool, error) {
return s.CreateRunTitled(ctx, d, key, workspace, tools, paths, input, RunOverrides{}, summarise.Title{}, retryOf...)
}
// CreateRunTitled inserts a run with the caller's title and launch-time model
// overrides. A non-empty title (a model generation) is stored verbatim; an empty
// one falls back to the prompt-derived title, so a run never stores an empty
// title. The overrides are compared in the request-key idempotency check, so a
// replay with different overrides is refused as a different run.
func (s *Store) CreateRunTitled(ctx context.Context, d *protocol.PipelineDetail, key, workspace string, tools bool, paths []string, input map[string]any, overrides RunOverrides, title summarise.Title, retryOf ...int64) (int64, bool, error) {
var parent int64
if len(retryOf) > 0 {
parent = retryOf[0]
}
if parent < 0 {
return 0, false, fmt.Errorf("invalid retry parent")
}
title = resolveRunTitle(title, input)
encoded, err := json.Marshal(input)
if err != nil {
return 0, false, err
}
writes, err := json.Marshal(paths)
if err != nil {
return 0, false, err
}
stageModels := overrides.StageModels
if stageModels == nil {
stageModels = map[string]string{}
}
encodedModels, err := json.Marshal(stageModels)
if err != nil {
return 0, false, err
}
s.mu.Lock()
defer s.mu.Unlock()
var id, pid int64
var version int
var oldInput, oldWorkspace, oldPaths, oldModel, oldStageModels string
var oldTools bool
err = s.db.QueryRowContext(ctx, "SELECT id,pipeline_id,version,input_json,workspace,write_paths,allow_tools,model,stage_models FROM pipeline_runs WHERE request_key=?", key).Scan(&id, &pid, &version, &oldInput, &oldWorkspace, &oldPaths, &oldTools, &oldModel, &oldStageModels)
if err == nil {
var oldParent int64
if err := s.db.QueryRowContext(ctx, "SELECT COALESCE((SELECT original_run_id FROM run_retries WHERE run_id=?),0)", id).Scan(&oldParent); err != nil {
return 0, false, err
}
if pid != d.ID || version != d.Version || oldInput != string(encoded) || oldWorkspace != workspace || oldPaths != string(writes) || oldTools != tools || oldParent != parent || oldModel != overrides.Model || oldStageModels != string(encodedModels) {
return 0, false, fmt.Errorf("request key already used for a different run")
}
return id, false, nil
}
if err != sql.ErrNoRows {
return 0, false, err
}
tx, err := s.db.BeginTx(ctx, nil)
if err != nil {
return 0, false, err
}
defer tx.Rollback()
result, err := tx.ExecContext(ctx, "INSERT INTO pipeline_runs(pipeline_id,version,request_key,workspace,allow_tools,write_paths,input_json,title,title_source,title_model,model,stage_models) VALUES (?,?,?,?,?,?,?,?,?,?,?,?)", d.ID, d.Version, key, workspace, tools, string(writes), string(encoded), title.Text, title.Source, title.Model, overrides.Model, string(encodedModels))
if err != nil {
return 0, false, err
}
id, err = result.LastInsertId()
if err != nil {
return 0, false, err
}
if parent > 0 {
if _, err := tx.ExecContext(ctx, "INSERT INTO run_retries(run_id,original_run_id) VALUES(?,?)", id, parent); err != nil {
return 0, false, err
}
}
if err := tx.Commit(); err != nil {
return 0, false, err
}
return id, true, nil
}
// runFrom is the shared pipeline_runs/pipelines join every run-row read builds
// on, so the run projections cannot drift.
const runFrom = `FROM pipeline_runs r JOIN pipelines p ON p.id=r.pipeline_id`
// runStamps formats a run row's created/finished timestamps; reused by runSelect
// and searchRuns instead of copied per query.
const runStamps = `strftime('%Y-%m-%dT%H:%M:%SZ',r.created_at),COALESCE(strftime('%Y-%m-%dT%H:%M:%SZ',r.finished_at),'')`
// resolveRunTitle guarantees a stored run title is never empty: a title supplied
// by the caller (a model generation) is kept verbatim, and an absent one is
// derived from the prompt's first line. The fallback is server-owned and never
// calls a model, so it can never block or fail run creation.
func resolveRunTitle(title summarise.Title, input map[string]any) summarise.Title {
if strings.TrimSpace(title.Text) != "" {
return title
}
prompt, _ := input["prompt"].(string)
return summarise.Title{Text: summarise.DeriveTitle(prompt), Source: summarise.SourceFallback}
}
// SetRunTitle replaces a run's operator-facing title and its provenance without
// touching the run's input, steps or execution. It is how an operator renames a
// run after the fact.
func (s *Store) SetRunTitle(ctx context.Context, id int64, title summarise.Title) error {
result, err := s.db.ExecContext(ctx, "UPDATE pipeline_runs SET title=?,title_source=?,title_model=? WHERE id=?", title.Text, title.Source, title.Model, id)
if err != nil {
return err
}
n, err := result.RowsAffected()
if err != nil {
return err
}
if n != 1 {
return fmt.Errorf("run not found")
}
return nil
}
const runSelect = `SELECT r.id,r.pipeline_id,p.name,r.version,v.content_hash,r.status,r.outcome,r.current_stage,
` + runStamps + `,r.diagnostic,
CASE WHEN r.status='succeeded' THEN r.output_json ELSE COALESCE((SELECT output_json FROM run_steps WHERE run_id=r.id AND status='completed' ORDER BY sequence DESC LIMIT 1),'{}') END,
(SELECT COUNT(*) FROM run_steps WHERE run_id=r.id AND status='completed'),r.workspace,r.title,r.model,r.stage_models
` + runFrom + ` JOIN pipeline_versions v ON v.pipeline_id=r.pipeline_id AND v.version=r.version`
func scanRun(row interface{ Scan(...any) error }, r *protocol.RunSummary) error {
var output, stageModels string
if err := row.Scan(&r.ID, &r.PipelineID, &r.Name, &r.Version, &r.ContentHash, &r.Status, &r.Outcome, &r.CurrentStage, &r.CreatedAt, &r.FinishedAt, &r.Diagnostic, &output, &r.CompletedSteps, &r.Workspace, &r.Title, &r.Model, &stageModels); err != nil {
return err
}
if stageModels != "" && stageModels != "{}" {
if err := json.Unmarshal([]byte(stageModels), &r.StageModels); err != nil {
return err
}
}
var values map[string]any
if err := decodeValues(output, &values); err != nil {
return err
}
r.ResultPreview = protocol.OutputPreview(values)
return nil
}
func (s *Store) ListRuns(ctx context.Context) ([]protocol.RunSummary, error) {
rows, err := s.db.QueryContext(ctx, runSelect+" ORDER BY r.id DESC")
if err != nil {
return nil, err
}
defer rows.Close()
items := []protocol.RunSummary{}
for rows.Next() {
var r protocol.RunSummary
if err := scanRun(rows, &r); err != nil {
return nil, err
}
items = append(items, r)
}
return items, rows.Err()
}
func (s *Store) RunByKey(ctx context.Context, key string) (int64, error) {
var id int64
err := s.db.QueryRowContext(ctx, "SELECT id FROM pipeline_runs WHERE request_key=?", key).Scan(&id)
if err == sql.ErrNoRows {
return 0, nil
}
return id, err
}
func decodeValues(text string, v *map[string]any) error {
d := json.NewDecoder(bytes.NewBufferString(text))
d.UseNumber()
return d.Decode(v)
}
func (s *Store) GetRun(ctx context.Context, id int64) (*protocol.RunDetail, error) {
tx, err := s.db.BeginTx(ctx, &sql.TxOptions{ReadOnly: true})
if err != nil {
return nil, err
}
defer tx.Rollback()
r := &protocol.RunDetail{}
if err := scanRun(tx.QueryRowContext(ctx, runSelect+" WHERE r.id=?", id), &r.RunSummary); err != nil {
if err == sql.ErrNoRows {
return nil, fmt.Errorf("run not found")
}
return nil, err
}
var input, output, paths string
var graphJSON string
if err := tx.QueryRowContext(ctx, "SELECT graph_json FROM pipeline_versions WHERE pipeline_id=? AND version=?", r.PipelineID, r.Version).Scan(&graphJSON); err != nil {
return nil, err
}
if err := json.Unmarshal([]byte(graphJSON), &r.Graph); err != nil {
return nil, err
}
if err := tx.QueryRowContext(ctx, "SELECT workspace,allow_tools,write_paths,input_json,output_json,COALESCE((SELECT original_run_id FROM run_retries WHERE run_id=pipeline_runs.id),0),title_source,title_model FROM pipeline_runs WHERE id=?", id).Scan(&r.Workspace, &r.AllowTools, &paths, &input, &output, &r.RetryOf, &r.TitleSource, &r.TitleModel); err != nil {
return nil, err
}
if err := decodeValues(input, &r.Input); err != nil {
return nil, err
}
if err := decodeValues(output, &r.Output); err != nil {
return nil, err
}
if err := json.Unmarshal([]byte(paths), &r.WritePaths); err != nil {
return nil, err
}
rows, err := tx.QueryContext(ctx, `SELECT sequence,stage_key,status,outcome,target,input_json,output_json,diagnostic,session_id,agent_active,transcript,provider,model,
COALESCE((SELECT receipts_json FROM step_notifications n WHERE n.run_id=run_steps.run_id AND n.sequence=run_steps.sequence),'[]'),
COALESCE((SELECT changes_json FROM step_file_changes f WHERE f.run_id=run_steps.run_id AND f.sequence=run_steps.sequence),'null'),
COALESCE((SELECT artifacts_json FROM step_artifacts a WHERE a.run_id=run_steps.run_id AND a.sequence=run_steps.sequence),'null'),
COALESCE((SELECT verdict_json FROM step_verdicts v WHERE v.run_id=run_steps.run_id AND v.sequence=run_steps.sequence),''),
strftime('%Y-%m-%dT%H:%M:%SZ',started_at),COALESCE(strftime('%Y-%m-%dT%H:%M:%SZ',finished_at),'') FROM run_steps WHERE run_id=? ORDER BY sequence`, id)
if err != nil {
return nil, err
}
r.Steps = []protocol.RunStep{}
for rows.Next() {
var step protocol.RunStep
var notifications string
var fileChanges, artifacts, storedVerdict string
if err := rows.Scan(&step.Sequence, &step.Stage, &step.Status, &step.Outcome, &step.Target, &input, &output, &step.Diagnostic, &step.SessionID, &step.AgentActive, &step.Transcript, &step.Provider, &step.Model, &notifications, &fileChanges, &artifacts, &storedVerdict, &step.StartedAt, &step.FinishedAt); err != nil {
rows.Close()
return nil, err
}
if err := json.Unmarshal([]byte(notifications), &step.Notifications); err != nil {
rows.Close()
return nil, err
}
if err := json.Unmarshal([]byte(fileChanges), &step.FileChanges); err != nil {
rows.Close()
return nil, err
}
if artifacts != "" && artifacts != "null" {
var evidence stageArtifactsEvidence
if err := json.Unmarshal([]byte(artifacts), &evidence); err != nil {
rows.Close()
return nil, err
}
step.Artifacts = evidence.Files
step.ArtifactsSkipped = evidence.Skipped
step.ArtifactsTruncated = evidence.Truncated
}
if err := decodeValues(input, &step.Input); err != nil {
rows.Close()
return nil, err
}
if err := decodeValues(output, &step.Output); err != nil {
rows.Close()
return nil, err
}
// The verdict is derived here - the one place that already holds both the
// decoded output and the recorded artifacts - using the stored model line
// when present and the bounded read-time fallback otherwise, so existing
// runs need no backfill.
var stored stageVerdictEvidence
if storedVerdict != "" {
if err := json.Unmarshal([]byte(storedVerdict), &stored); err != nil {
rows.Close()
return nil, err
}
}
step.Verdict = protocol.NewStageVerdict(step.Outcome, step.Target, step.Output, step.Artifacts, stored.Reason, stored.Source)
// Loaded below after the rows cursor closes to preserve SQLite connection use.
r.Steps = append(r.Steps, step)
}
err = rows.Err()
rows.Close()
if err != nil {
return nil, err
}
for i := range r.Steps {
var data string
err := tx.QueryRowContext(ctx, "SELECT evidence_json FROM step_control WHERE run_id=? AND sequence=?", id, r.Steps[i].Sequence).Scan(&data)
if err == sql.ErrNoRows {
continue
}
if err != nil {
return nil, err
}
if err := json.Unmarshal([]byte(data), &r.Steps[i].Control); err != nil {
return nil, err
}
}
if err := tx.Commit(); err != nil {
return nil, err
}
return r, nil
}
func (s *Store) SaveNotifications(ctx context.Context, id int64, sequence int, receipts []protocol.NotificationReceipt) error {
data, err := json.Marshal(receipts)
if err != nil {
return err
}
_, err = s.db.ExecContext(ctx, `INSERT INTO step_notifications(run_id,sequence,receipts_json) VALUES(?,?,?) ON CONFLICT(run_id,sequence) DO UPDATE SET receipts_json=excluded.receipts_json`, id, sequence, string(data))
return err
}
func affected(result sql.Result, err error) error {
if err != nil {
return err
}
n, err := result.RowsAffected()
if err != nil {
return err
}
if n != 1 {
return fmt.Errorf("invalid run state transition")
}
return nil
}
func (s *Store) BeginStep(ctx context.Context, id int64, sequence int, key string, input map[string]any) error {
encoded, err := json.Marshal(input)
if err != nil {
return err
}
tx, err := s.db.BeginTx(ctx, nil)
if err != nil {
return err
}
defer tx.Rollback()
if err := affected(tx.ExecContext(ctx, "UPDATE pipeline_runs SET status='running',current_stage=? WHERE id=? AND status IN ('queued','running')", key, id)); err != nil {
return err
}
if _, err := tx.ExecContext(ctx, "INSERT INTO run_steps(run_id,sequence,stage_key,input_json) VALUES (?,?,?,?)", id, sequence, key, string(encoded)); err != nil {
return err
}
return tx.Commit()
}
func (s *Store) RunSession(ctx context.Context, id int64, sequence int, session string, active bool, metadata ...string) error {
tx, err := s.db.BeginTx(ctx, nil)
if err != nil {
return err
}
defer tx.Rollback()
if err = affected(tx.ExecContext(ctx, "UPDATE run_steps SET session_id=?,agent_active=? WHERE run_id=? AND sequence=? AND status='running'", session, active, id, sequence)); err != nil {
return err
}
if len(metadata) > 0 {
backend := metadata[0]
if backend == "" {
backend = "v2"
}
reference := ""
if len(metadata) > 1 {
reference = metadata[1]
}
if _, err = tx.ExecContext(ctx, "INSERT INTO run_session_owners(run_id,sequence,backend,reference) VALUES(?,?,?,?) ON CONFLICT(run_id,sequence) DO UPDATE SET backend=excluded.backend,reference=excluded.reference", id, sequence, backend, reference); err != nil {
return err
}
}
return tx.Commit()
}
type SessionOwner struct {
ID string
Backend string
Directory string
Reference string
// RunID is the owning run, used to tell an orphaned session (no active run)
// from one owned by a run that is active right now.
RunID int64
// Active is true while the owning step records the session as agent-active.
Active bool
}
func (s *Store) RunSessionOwner(ctx context.Context, id int64, sequence int) (SessionOwner, error) {
var owner SessionOwner
err := s.db.QueryRowContext(ctx, `SELECT s.session_id,COALESCE(o.backend,'v2'),r.workspace,COALESCE(o.reference,'') FROM run_steps s JOIN pipeline_runs r ON r.id=s.run_id LEFT JOIN run_session_owners o ON o.run_id=s.run_id AND o.sequence=s.sequence WHERE s.run_id=? AND s.sequence=?`, id, sequence).Scan(&owner.ID, &owner.Backend, &owner.Directory, &owner.Reference)
return owner, err
}
// sessionOwnerScanLimit bounds the ownership scan so a long-lived database with
// thousands of historical sessions cannot make one chat_sessions request scan
// them all. Rows are read newest-run first, so the bound only ever drops the
// oldest owners, never the sessions a client can still be writing.
const sessionOwnerScanLimit = 1024
// ActiveSessionOwners reports every currently active agent session, deduped by
// session id (newest owning run wins).
func (s *Store) ActiveSessionOwners(ctx context.Context) ([]SessionOwner, error) {
return s.sessionOwners(ctx, true)
}
// OwnedSessions reports every session the server ever recorded in run_steps,
// deduped by session id (newest owning run wins) and including inactive ones, so
// chat_sessions can be restricted to sessions this server created.
func (s *Store) OwnedSessions(ctx context.Context) ([]SessionOwner, error) {
return s.sessionOwners(ctx, false)
}
// sessionOwners is the single ownership query both ActiveSessionOwners and
// OwnedSessions run, so the SQL is not duplicated. It reads one bounded,
// newest-run-first window and drops repeated session ids in favour of the most
// recent owning run's directory and active flag.
func (s *Store) sessionOwners(ctx context.Context, activeOnly bool) ([]SessionOwner, error) {
query := `SELECT s.session_id,COALESCE(o.backend,'v2'),r.workspace,COALESCE(o.reference,''),s.run_id,s.agent_active
FROM run_steps s JOIN pipeline_runs r ON r.id=s.run_id LEFT JOIN run_session_owners o ON o.run_id=s.run_id AND o.sequence=s.sequence WHERE s.session_id<>''`
if activeOnly {
query += " AND s.agent_active=1"
}
query += " ORDER BY s.run_id DESC LIMIT ?"
rows, err := s.db.QueryContext(ctx, query, sessionOwnerScanLimit)
if err != nil {
return nil, err
}
defer rows.Close()
seen := map[string]struct{}{}
var owners []SessionOwner
for rows.Next() {
var owner SessionOwner
var active int
if err = rows.Scan(&owner.ID, &owner.Backend, &owner.Directory, &owner.Reference, &owner.RunID, &active); err != nil {
return nil, err
}
owner.Active = active != 0
if _, ok := seen[owner.ID]; ok {
continue
}
seen[owner.ID] = struct{}{}
owners = append(owners, owner)
}
return owners, rows.Err()
}
// stageArtifactsEvidence is the persisted per-step artifact list plus its
// bounded-scan counters; it is kept in a separate table like the other
// step-scoped evidence so run_steps needs no schema migration on old databases.
type stageArtifactsEvidence struct {
Files []protocol.StageArtifact `json:"files"`
Skipped int `json:"skipped,omitempty"`
Truncated int `json:"truncated,omitempty"`
}
// stageVerdictEvidence is the generated one-line verdict reason plus its
// provenance. Like the other step-scoped evidence it lives in its own table, so
// run_steps needs no schema migration and an old database gains the empty table
// on Open with no backfill. Only a model-generated line is ever stored; the
// read-time fallback is always derived, so existing runs still show a verdict.
type stageVerdictEvidence struct {
Reason string `json:"reason"`
Source string `json:"source"`
}
func (s *Store) FinishStep(ctx context.Context, id int64, step protocol.RunStep) error {
output, err := json.Marshal(step.Output)
if err != nil {
return err
}
// Bound the stored transcript without corrupting structured JSON. A large
// transcript becomes a valid bounded preview envelope preserving stage_limits
// and failure/format diagnostics; the exact Output is saved separately below.
step.Transcript = stage.BoundTranscript(step.Transcript, step.SessionID)
tx, err := s.db.BeginTx(ctx, nil)
if err != nil {
return err
}
defer tx.Rollback()
if err := affected(tx.ExecContext(ctx, `UPDATE run_steps SET status=?,outcome=?,target=?,output_json=?,diagnostic=?,transcript=?,provider=?,model=?,finished_at=CURRENT_TIMESTAMP
WHERE run_id=? AND sequence=? AND status='running'`, step.Status, step.Outcome, step.Target, string(output), step.Diagnostic, step.Transcript, step.Provider, step.Model, id, step.Sequence)); err != nil {
return err
}
if step.FileChanges != nil {
data, err := json.Marshal(step.FileChanges)
if err != nil {
return err
}
if _, err = tx.ExecContext(ctx, "INSERT INTO step_file_changes(run_id,sequence,changes_json) VALUES(?,?,?)", id, step.Sequence, string(data)); err != nil {
return err
}
}
if step.Control != nil {
data, err := json.Marshal(step.Control)
if err != nil {
return err
}
if _, err := tx.ExecContext(ctx, "INSERT INTO step_control(run_id,sequence,evidence_json) VALUES(?,?,?)", id, step.Sequence, string(data)); err != nil {
return err
}
}
if len(step.Artifacts) > 0 || step.ArtifactsSkipped > 0 || step.ArtifactsTruncated > 0 {
data, err := json.Marshal(stageArtifactsEvidence{Files: step.Artifacts, Skipped: step.ArtifactsSkipped, Truncated: step.ArtifactsTruncated})
if err != nil {
return err
}
if _, err := tx.ExecContext(ctx, "INSERT INTO step_artifacts(run_id,sequence,artifacts_json) VALUES(?,?,?)", id, step.Sequence, string(data)); err != nil {
return err
}
}
// Persist only a generated model line and its provenance; the read-time
// fallback is always derived in GetRun, so old runs stay intact.
if step.Verdict != nil && strings.TrimSpace(step.Verdict.Reason) != "" {
data, err := json.Marshal(stageVerdictEvidence{Reason: step.Verdict.Reason, Source: step.Verdict.ReasonSource})
if err != nil {
return err
}
if _, err := tx.ExecContext(ctx, "INSERT INTO step_verdicts(run_id,sequence,verdict_json) VALUES(?,?,?) ON CONFLICT(run_id,sequence) DO UPDATE SET verdict_json=excluded.verdict_json", id, step.Sequence, string(data)); err != nil {
return err
}
}
return tx.Commit()
}
// MarkWaiting persists a human stage's pending state in one transaction: the
// step becomes waiting with self-contained evidence (its operator instructions
// and ordered options) and the run reports the same key it is waiting on. It
// leaves finished_at NULL for both and adds no goroutine, timer or new column.
func (s *Store) MarkWaiting(ctx context.Context, id int64, sequence int, key string, evidence map[string]any) error {
data, err := json.Marshal(evidence)
if err != nil {
return err
}
tx, err := s.db.BeginTx(ctx, nil)
if err != nil {
return err
}
defer tx.Rollback()
if err := affected(tx.ExecContext(ctx, `UPDATE run_steps SET status=?,output_json=? WHERE run_id=? AND sequence=? AND status='running'`,
protocol.StepStatusWaiting, string(data), id, sequence)); err != nil {
return err
}
if err := affected(tx.ExecContext(ctx, `UPDATE pipeline_runs SET status=?,current_stage=? WHERE id=? AND status IN ('queued','running')`,
protocol.RunStatusWaiting, key, id)); err != nil {
return err
}
return tx.Commit()
}
// ResolveDecision records an operator's choice for a waiting human stage and
// routes the run along that option's edge, all in one short transaction. It
// reads the pinned graph and the pending step from persisted rows, so it is
// correct after a restart and needs no live goroutine. Validation is idempotent:
// a repeated decision for an already-decided visit with the same option returns
// applied=false and no error, an unknown option is refused with the valid list,
// and a stage that is not waiting is refused with its current state.
func (s *Store) ResolveDecision(ctx context.Context, id int64, stageKey, option, feedback string) (protocol.RunStep, bool, error) {
tx, err := s.db.BeginTx(ctx, nil)
if err != nil {
return protocol.RunStep{}, false, err
}
defer tx.Rollback()
var status, currentStage, graphJSON string
if err := tx.QueryRowContext(ctx, `SELECT r.status,r.current_stage,v.graph_json FROM pipeline_runs r
JOIN pipeline_versions v ON v.pipeline_id=r.pipeline_id AND v.version=r.version WHERE r.id=?`, id).Scan(&status, &currentStage, &graphJSON); err != nil {
if err == sql.ErrNoRows {
return protocol.RunStep{}, false, fmt.Errorf("run not found")
}
return protocol.RunStep{}, false, err
}
if stageKey == "" {
stageKey = currentStage
// Prefer the actual waiting step's stage; current_stage is normally the
// waiting stage, but this keeps the decision correct if it ever drifts.
var waitingKey string
if err := tx.QueryRowContext(ctx, `SELECT stage_key FROM run_steps WHERE run_id=? AND status=? ORDER BY sequence DESC LIMIT 1`, id, protocol.StepStatusWaiting).Scan(&waitingKey); err == nil {
stageKey = waitingKey
} else if err != sql.ErrNoRows {
return protocol.RunStep{}, false, err
}
}
var graph protocol.Graph
if err := json.Unmarshal([]byte(graphJSON), &graph); err != nil {
return protocol.RunStep{}, false, err
}
var edges map[string]string
found := false
for _, declared := range graph.Stages {
if declared.Key == stageKey {
edges = declared.Edges
found = true
break
}
}
if !found {
return protocol.RunStep{}, false, fmt.Errorf("stage %q is not part of this run", stageKey)
}
options := stage.HumanOptions(edges)
valid := false
for _, candidate := range options {
if candidate == option {
valid = true
break
}
}
if !valid {
return protocol.RunStep{}, false, fmt.Errorf("unknown option %q for stage %s; valid options: %s", option, stageKey, strings.Join(options, ", "))
}
var sequence int
var stepStatus, stepOutcome string
err = tx.QueryRowContext(ctx, `SELECT sequence,status,outcome FROM run_steps WHERE run_id=? AND stage_key=? ORDER BY sequence DESC LIMIT 1`, id, stageKey).Scan(&sequence, &stepStatus, &stepOutcome)
if err == sql.ErrNoRows {
return protocol.RunStep{}, false, fmt.Errorf("stage %s is not waiting", stageKey)
}
if err != nil {
return protocol.RunStep{}, false, err
}
if stepStatus != protocol.StepStatusWaiting {
if stepStatus == "completed" && stepOutcome == option {
return protocol.RunStep{Sequence: sequence, Stage: stageKey, Status: "completed", Outcome: stepOutcome, Target: edges[stepOutcome]}, false, nil
}
return protocol.RunStep{}, false, fmt.Errorf("stage %s is not waiting (state %s)", stageKey, stepStatus)
}
if status != protocol.RunStatusWaiting && status != protocol.RunStatusRunning {
return protocol.RunStep{}, false, fmt.Errorf("run %d is not waiting (state %s)", id, status)
}
target := edges[option]
// The operator's choice and feedback are the step's evidence. The feedback
// stays in the output only - never the step diagnostic - so a deliberate,
// successful decision is not presented as a stop or error; the derived
// verdict reads the feedback as the step's reason.
output := map[string]any{protocol.DecisionOptionKey: option, protocol.DecisionFeedbackKey: feedback}
encoded, err := json.Marshal(output)
if err != nil {
return protocol.RunStep{}, false, err
}
if err := affected(tx.ExecContext(ctx, `UPDATE run_steps SET status='completed',outcome=?,target=?,output_json=?,finished_at=CURRENT_TIMESTAMP
WHERE run_id=? AND sequence=? AND status=?`, option, target, string(encoded), id, sequence, protocol.StepStatusWaiting)); err != nil {
return protocol.RunStep{}, false, err
}
if err := affected(tx.ExecContext(ctx, `UPDATE pipeline_runs SET status='running' WHERE id=? AND status IN (?,?)`, id, protocol.RunStatusWaiting, protocol.RunStatusRunning)); err != nil {
return protocol.RunStep{}, false, err
}
if err := tx.Commit(); err != nil {
return protocol.RunStep{}, false, err
}
return protocol.RunStep{Sequence: sequence, Stage: stageKey, Status: "completed", Outcome: option, Target: target, Output: output}, true, nil
}
// CancelWaiting cancels a run that is waiting on a person without a live
// goroutine. It is a single transaction that marks the run canceled and its
// waiting step canceled; a run that is not waiting is reported, not silently
// ignored.
func (s *Store) CancelWaiting(ctx context.Context, id int64) error {
tx, err := s.db.BeginTx(ctx, nil)
if err != nil {
return err
}
defer tx.Rollback()
res, err := tx.ExecContext(ctx, `UPDATE pipeline_runs SET status='canceled',finished_at=CURRENT_TIMESTAMP WHERE id=? AND status=?`, id, protocol.RunStatusWaiting)
if err != nil {
return err
}
n, err := res.RowsAffected()
if err != nil {
return err
}
if n != 1 {
return fmt.Errorf("run is not active or waiting")
}
if _, err := tx.ExecContext(ctx, `UPDATE run_steps SET status='canceled',diagnostic='Canceled while waiting for a decision',finished_at=CURRENT_TIMESTAMP WHERE run_id=? AND status=?`, id, protocol.StepStatusWaiting); err != nil {
return err
}
return tx.Commit()
}
func (s *Store) FinishRun(ctx context.Context, id int64, status, outcome, diagnostic string, output map[string]any) error {
data, err := json.Marshal(output)
if err != nil {
return err
}
return affected(s.db.ExecContext(ctx, "UPDATE pipeline_runs SET status=?,outcome=?,diagnostic=?,output_json=?,finished_at=CURRENT_TIMESTAMP WHERE id=? AND status IN ('queued','running')", status, outcome, diagnostic, string(data), id))
}
// ActiveAgentSessionsForRun returns the distinct active agent session ids that
// belong to one run. It is scoped to run_steps.run_id so concurrent runs never
// observe each other's sessions: run_steps is keyed by (run_id, sequence), so
// this is one indexed lookup, not a scan.
func (s *Store) ActiveAgentSessionsForRun(ctx context.Context, runID int64) ([]string, error) {
rows, err := s.db.QueryContext(ctx, "SELECT DISTINCT session_id FROM run_steps WHERE run_id=? AND agent_active=1 AND session_id<>''", runID)
if err != nil {
return nil, err
}
defer rows.Close()
ids := []string{}
for rows.Next() {
var id string
if err := rows.Scan(&id); err != nil {
return nil, err
}
ids = append(ids, id)
}
return ids, rows.Err()
}
func (s *Store) RecoverRuns(ctx context.Context) error {
tx, err := s.db.BeginTx(ctx, nil)
if err != nil {
return err
}
defer tx.Rollback()
if _, err := tx.ExecContext(ctx, "UPDATE run_steps SET status='interrupted',agent_active=0,diagnostic='Server stopped; stage was not resumed',finished_at=CURRENT_TIMESTAMP WHERE (status='running' OR agent_active=1) AND status<>?", protocol.StepStatusWaiting); err != nil {
return err
}
if _, err := tx.ExecContext(ctx, "UPDATE pipeline_runs SET status='interrupted',diagnostic='Server stopped; run was not resumed',finished_at=CURRENT_TIMESTAMP WHERE status IN ('queued','running') AND status<>?", protocol.RunStatusWaiting); err != nil {
return err
}
return tx.Commit()
}