mirror of
https://github.com/multica-ai/multica.git
synced 2026-07-05 13:29:44 +02:00
45dd094d61
Round-2 review feedback on PR #2256: 1. Add explicit dirty-bucket queue (task_usage_daily_dirty) populated by triggers on agent_task_queue (UPDATE OF runtime_id, DELETE) and task_usage (DELETE). The rollup window function drains both this queue and the updated_at-based discovery, so runtime reassignment and issue-cascade deletes no longer leave the rollup divergent from the raw query. Triggers join via agent (not issue) to look up workspace_id, because when the cascade comes from issue, the issue row is already gone by the time atq's BEFORE DELETE fires; agent stays alive. 2. Make migration 072 online-safe: only ADD COLUMN updated_at TIMESTAMPTZ (nullable, no default → metadata-only ALTER, no row rewrite) and a separate ALTER for SET DEFAULT now() (also metadata-only). No bulk UPDATE on the hot task_usage table. The rollup window function's dirty_keys CTE handles legacy NULL rows via an OR branch, supported by partial index idx_task_usage_created_at_legacy. 3. Refresh stale documentation in cmd/backfill_task_usage_daily/main.go header to describe the current recompute/replace semantics, idempotent re-runnability, and the actual migration numbering (072..077). Tests: - TestRollupTaskUsageDaily_InvalidationOnReassign: verifies usage moves between runtime buckets after ReassignTasksToRuntime-style update. - TestRollupTaskUsageDaily_InvalidationOnIssueDelete: verifies daily bucket is cleared after issue delete cascades through atq → task_usage. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Co-authored-by: multica-agent <github@multica.ai>
70 lines
3.0 KiB
SQL
70 lines
3.0 KiB
SQL
-- name: UpsertTaskUsage :exec
|
|
-- Bumps `updated_at` on INSERT and on conflict so the daily-rollup worker
|
|
-- (migration 073) detects the row as dirty and re-aggregates its bucket.
|
|
-- Without the conflict-side bump, a correction to historical token counts
|
|
-- would never propagate to the rollup.
|
|
INSERT INTO task_usage (task_id, provider, model, input_tokens, output_tokens, cache_read_tokens, cache_write_tokens, updated_at)
|
|
VALUES ($1, $2, $3, $4, $5, $6, $7, now())
|
|
ON CONFLICT (task_id, provider, model)
|
|
DO UPDATE SET
|
|
input_tokens = EXCLUDED.input_tokens,
|
|
output_tokens = EXCLUDED.output_tokens,
|
|
cache_read_tokens = EXCLUDED.cache_read_tokens,
|
|
cache_write_tokens = EXCLUDED.cache_write_tokens,
|
|
updated_at = now();
|
|
|
|
-- name: GetTaskUsage :many
|
|
SELECT * FROM task_usage
|
|
WHERE task_id = $1
|
|
ORDER BY model;
|
|
|
|
-- name: GetWorkspaceUsageByDay :many
|
|
-- Bucket by tu.created_at (usage report time, ~= task completion time), not
|
|
-- atq.created_at (task enqueue time), so tasks that queue one day and execute
|
|
-- the next are attributed to the day tokens were actually produced. The since
|
|
-- cutoff is truncated to start-of-day so `days=N` yields full calendar days.
|
|
SELECT
|
|
DATE(tu.created_at) AS date,
|
|
tu.model,
|
|
SUM(tu.input_tokens)::bigint AS total_input_tokens,
|
|
SUM(tu.output_tokens)::bigint AS total_output_tokens,
|
|
SUM(tu.cache_read_tokens)::bigint AS total_cache_read_tokens,
|
|
SUM(tu.cache_write_tokens)::bigint AS total_cache_write_tokens,
|
|
COUNT(DISTINCT tu.task_id)::int AS task_count
|
|
FROM task_usage tu
|
|
JOIN agent_task_queue atq ON atq.id = tu.task_id
|
|
JOIN agent a ON a.id = atq.agent_id
|
|
WHERE a.workspace_id = $1
|
|
AND tu.created_at >= DATE_TRUNC('day', @since::timestamptz)
|
|
GROUP BY DATE(tu.created_at), tu.model
|
|
ORDER BY DATE(tu.created_at) DESC, tu.model;
|
|
|
|
-- name: GetWorkspaceUsageSummary :many
|
|
-- Filter by tu.created_at (usage report time), aligned to start-of-day, so
|
|
-- `days=N` is interpreted as N full calendar days like the other usage queries.
|
|
SELECT
|
|
tu.model,
|
|
SUM(tu.input_tokens)::bigint AS total_input_tokens,
|
|
SUM(tu.output_tokens)::bigint AS total_output_tokens,
|
|
SUM(tu.cache_read_tokens)::bigint AS total_cache_read_tokens,
|
|
SUM(tu.cache_write_tokens)::bigint AS total_cache_write_tokens,
|
|
COUNT(DISTINCT tu.task_id)::int AS task_count
|
|
FROM task_usage tu
|
|
JOIN agent_task_queue atq ON atq.id = tu.task_id
|
|
JOIN agent a ON a.id = atq.agent_id
|
|
WHERE a.workspace_id = $1
|
|
AND tu.created_at >= DATE_TRUNC('day', @since::timestamptz)
|
|
GROUP BY tu.model
|
|
ORDER BY (SUM(tu.input_tokens) + SUM(tu.output_tokens)) DESC;
|
|
|
|
-- name: GetIssueUsageSummary :one
|
|
SELECT
|
|
COALESCE(SUM(tu.input_tokens), 0)::bigint AS total_input_tokens,
|
|
COALESCE(SUM(tu.output_tokens), 0)::bigint AS total_output_tokens,
|
|
COALESCE(SUM(tu.cache_read_tokens), 0)::bigint AS total_cache_read_tokens,
|
|
COALESCE(SUM(tu.cache_write_tokens), 0)::bigint AS total_cache_write_tokens,
|
|
COUNT(DISTINCT tu.task_id)::int AS task_count
|
|
FROM task_usage tu
|
|
JOIN agent_task_queue atq ON atq.id = tu.task_id
|
|
WHERE atq.issue_id = $1;
|