mirror of
https://github.com/BaaRai/ARTEX.git
synced 2026-11-13 11:40:53 +08:00
BaaRai
cf369dec4f
Adds GET /api/tasks/{id}/outcome: finding disposition and severity,
retest verdicts, result-row token totals, tool calls, skill misses, and
wall time in one row. This is the measurement layer an RSI loop needs
before claiming a change helped; it alters no agent behavior.
Metric selection follows harness2 (Google Research, Apache-2.0,
arXiv 2610.14224) and the task-gain / retained-gain / improver-gain
taxonomy in the awesome-rsi list.
32 lines
804 B
Go
32 lines
804 B
Go
package server
|
|
|
|
import (
|
|
"database/sql"
|
|
"errors"
|
|
"log"
|
|
"net/http"
|
|
"strconv"
|
|
)
|
|
|
|
// taskOutcome returns one task's production and cost baseline. It is the
|
|
// measurement layer for later RSI comparisons (harness2, Google Research,
|
|
// arXiv 2610.14224): nothing here changes agent behavior.
|
|
func (s *Server) taskOutcome(w http.ResponseWriter, r *http.Request) {
|
|
id, err := strconv.ParseInt(r.PathValue("id"), 10, 64)
|
|
if err != nil || id <= 0 {
|
|
writeErr(w, 400, "invalid task id")
|
|
return
|
|
}
|
|
outcome, err := s.m.PG().TaskOutcome(r.Context(), id)
|
|
if errors.Is(err, sql.ErrNoRows) {
|
|
writeErr(w, 404, "task not found")
|
|
return
|
|
}
|
|
if err != nil {
|
|
log.Printf("[tasks] outcome query failed for %d: %v", id, err)
|
|
writeErr(w, 500, "outcome query failed")
|
|
return
|
|
}
|
|
writeJSON(w, 200, outcome)
|
|
}
|