opensource/coder
3
0
Fork 0
mirror of https://github.com/coder/coder.git synced 2026-09-24 15:04:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: add columns for cached tokens from aibridge (#23832)

Browse Source 
Two new columns added to aibridge_token_usages:
  - cache_read_input_tokens (BIGINT, default 0)
  - cache_write_input_tokens (BIGINT, default 0)

Migration backfills existing rows by extracting values from the metadata
JSONB column (cache_read_input, input_cached, prompt_cached for reads
(max value selected since only 1 should be set), cache_creation_input
for writes).

All references to data from metadata were updated to reference new
columns. No other changes then changing where data is extracted from.

Requires aibridge library version bump to include:
https://github.com/coder/aibridge/pull/229
Fixes: https://github.com/coder/aibridge/issues/150
This commit is contained in:
Paweł Banaszewski
2026-04-03 16:27:31 +02:00
committed by GitHub
parent da3c46b557
commit 8369fa88fd
28 changed files with 423 additions and 212 deletions
Download Patch File Download Diff File Expand all files Collapse all files
coderd/database/queries/aibridge.sql
+9 -18
View File
@@ -31,9 +31,9 @@ WHERE aibridge_interceptions.id = (
-- name: InsertAIBridgeTokenUsage :one
INSERT INTO aibridge_token_usages (
id, interception_id, provider_response_id, input_tokens, output_tokens, metadata, created_at
id, interception_id, provider_response_id, input_tokens, output_tokens, cache_read_input_tokens, cache_write_input_tokens, metadata, created_at
) VALUES (
@id, @interception_id, @provider_response_id, @input_tokens, @output_tokens, COALESCE(@metadata::jsonb, '{}'::jsonb), @created_at
@id, @interception_id, @provider_response_id, @input_tokens, @output_tokens, @cache_read_input_tokens, @cache_write_input_tokens, COALESCE(@metadata::jsonb, '{}'::jsonb), @created_at
)
RETURNING *;
@@ -299,21 +299,8 @@ token_aggregates AS (
SELECT
COALESCE(SUM(tu.input_tokens), 0) AS token_count_input,
COALESCE(SUM(tu.output_tokens), 0) AS token_count_output,
-- Cached tokens are stored in metadata JSON, extract if available.
-- Read tokens may be stored in:
-- - cache_read_input (Anthropic)
-- - prompt_cached (OpenAI)
COALESCE(SUM(
COALESCE((tu.metadata->>'cache_read_input')::bigint, 0) +
COALESCE((tu.metadata->>'prompt_cached')::bigint, 0)
), 0) AS token_count_cached_read,
-- Written tokens may be stored in:
-- - cache_creation_input (Anthropic)
-- Note that cache_ephemeral_5m_input and cache_ephemeral_1h_input on
-- Anthropic are included in the cache_creation_input field.
COALESCE(SUM(
COALESCE((tu.metadata->>'cache_creation_input')::bigint, 0)
), 0) AS token_count_cached_written,
COALESCE(SUM(tu.cache_read_input_tokens), 0) AS token_count_cached_read,
COALESCE(SUM(tu.cache_write_input_tokens), 0) AS token_count_cached_written,
COUNT(tu.id) AS token_usages_count
FROM
interceptions_in_range i
@@ -552,6 +539,8 @@ SELECT
sp.threads,
COALESCE(st.input_tokens, 0)::bigint AS input_tokens,
COALESCE(st.output_tokens, 0)::bigint AS output_tokens,
COALESCE(st.cache_read_input_tokens, 0)::bigint AS cache_read_input_tokens,
COALESCE(st.cache_write_input_tokens, 0)::bigint AS cache_write_input_tokens,
COALESCE(slp.prompt, '') AS last_prompt
FROM
session_page sp
@@ -573,7 +562,9 @@ LEFT JOIN LATERAL (
-- Aggregate tokens only for this session's interceptions.
SELECT
COALESCE(SUM(tu.input_tokens), 0)::bigint AS input_tokens,
COALESCE(SUM(tu.output_tokens), 0)::bigint AS output_tokens
COALESCE(SUM(tu.output_tokens), 0)::bigint AS output_tokens,
COALESCE(SUM(tu.cache_read_input_tokens), 0)::bigint AS cache_read_input_tokens,
COALESCE(SUM(tu.cache_write_input_tokens), 0)::bigint AS cache_write_input_tokens
FROM aibridge_token_usages tu
WHERE tu.interception_id = ANY(sr.interception_ids)
) st ON true