mirror of
https://github.com/coder/coder.git
synced 2026-09-24 15:04:27 +08:00
feat: track step runtime_ms on chat messages (#23219)
## Summary Adds a `runtime_ms` column to `chat_messages` that records the wall-clock duration (in milliseconds) of each LLM step. This covers LLM streaming, tool execution, and retries — the full time the agent is "alive" for a step. This is the foundation for billing by agent alive time. The column follows the same pattern as `total_cost_micros`: stored per assistant message, aggregatable with `SUM()` over time periods by user. ## Changes - **Migration**: adds nullable `runtime_ms bigint` to `chat_messages`. - **chatloop**: adds `Runtime time.Duration` field to `PersistedStep`, measures `time.Since(stepStart)` at the beginning of each step (covering stream + tool execution + retries). - **chatd**: passes `step.Runtime.Milliseconds()` to the assistant message `InsertChatMessage` call; all other message types (system, user, tool) get `NULL`. - **Tests**: adds `runtime > 0` assertion in chatloop tests. ## Billing query pattern Once ready, aggregation mirrors the existing cost queries: ```sql SELECT COALESCE(SUM(cm.runtime_ms), 0)::bigint AS total_runtime_ms FROM chat_messages cm JOIN chats c ON c.id = cm.chat_id WHERE c.owner_id = @user_id AND cm.created_at >= @start_time AND cm.created_at < @end_time AND cm.runtime_ms IS NOT NULL; ```
This commit is contained in:
@@ -42,6 +42,11 @@ type PersistedStep struct {
|
||||
Content []fantasy.Content
|
||||
Usage fantasy.Usage
|
||||
ContextLimit sql.NullInt64
|
||||
// Runtime is the wall-clock duration of this step,
|
||||
// covering LLM streaming, tool execution, and retries.
|
||||
// Zero indicates the duration was not measured (e.g.
|
||||
// interrupted steps).
|
||||
Runtime time.Duration
|
||||
}
|
||||
|
||||
// RunOptions configures a single streaming chat loop run.
|
||||
@@ -260,6 +265,7 @@ func Run(ctx context.Context, opts RunOptions) error {
|
||||
|
||||
for step := 0; totalSteps < opts.MaxSteps; step++ {
|
||||
totalSteps++
|
||||
stepStart := time.Now()
|
||||
// Copy messages so that provider-specific caching
|
||||
// mutations don't leak back to the caller's slice.
|
||||
// copy copies Message structs by value, so field
|
||||
@@ -365,6 +371,7 @@ func Run(ctx context.Context, opts RunOptions) error {
|
||||
Content: result.content,
|
||||
Usage: result.usage,
|
||||
ContextLimit: contextLimit,
|
||||
Runtime: time.Since(stepStart),
|
||||
}); err != nil {
|
||||
if errors.Is(err, ErrInterrupted) {
|
||||
persistInterruptedStep(ctx, opts, &result)
|
||||
|
||||
@@ -7,6 +7,7 @@ import (
|
||||
"strings"
|
||||
"sync"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"charm.land/fantasy"
|
||||
fantasyanthropic "charm.land/fantasy/providers/anthropic"
|
||||
@@ -64,6 +65,8 @@ func TestRun_ActiveToolsPrepareBehavior(t *testing.T) {
|
||||
require.Equal(t, 1, persistStepCalls)
|
||||
require.True(t, persistedStep.ContextLimit.Valid)
|
||||
require.Equal(t, int64(4096), persistedStep.ContextLimit.Int64)
|
||||
require.Greater(t, persistedStep.Runtime, time.Duration(0),
|
||||
"step runtime should be positive")
|
||||
|
||||
require.NotEmpty(t, capturedCall.Prompt)
|
||||
require.False(t, containsPromptSentinel(capturedCall.Prompt))
|
||||
|
||||
Reference in New Issue
Block a user