dguiducci/Skald-Circle
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

llm request tracking, user context cleanup, minor fixes

Browse Source
This commit is contained in:
dguiducci
2026-07-11 00:23:14 +01:00
parent 5936cf0b2e
commit 587958ffe0
24 changed files with 402 additions and 347 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/skald-core/src/db/llm_request_payloads.rs
+32
View File
@@ -0,0 +1,32 @@
//! DB operations for the `llm_request_payloads` table (owner bucket).
//!
//! Full request/response payloads + headers for each LLM call. Lives in
//! `{userid}.db` (encrypted), correlated with the metadata row in `system.db`
//! via `request_id`.
use anyhow::Result;
use sqlx::SqlitePool;
pub struct PayloadRow {
pub request_json: String,
pub request_headers: Option<String>,
pub response_json: Option<String>,
pub response_headers: Option<String>,
pub request_id: String,
}
pub async fn insert(pool: &SqlitePool, row: PayloadRow) -> Result<()> {
sqlx::query(
"INSERT INTO llm_request_payloads
(request_id, request_json, request_headers, response_json, response_headers)
VALUES (?, ?, ?, ?, ?)",
)
.bind(&row.request_id)
.bind(&row.request_json)
.bind(&row.request_headers)
.bind(&row.response_json)
.bind(&row.response_headers)
.execute(pool)
.await?;
Ok(())
}
crates/skald-core/src/db/llm_requests/cleanup.rs
+5 -26
View File
@@ -1,9 +1,9 @@
//! Background maintenance task for the `llm_requests` table.
//!
//! Periodically nulls out old payloads/headers and deletes expired rows according
//! to the retention settings in [`LlmRequestsLogConfig`], then `VACUUM`s to reclaim
//! freed pages. Extracted from `Skald::new` so the loop lives next to the queries it
//! calls; the returned handle is registered with the `TaskSupervisor` for shutdown.
//! Deletes expired metadata rows according to the retention settings in
//! [`LlmRequestsLogConfig`], then `VACUUM`s to reclaim freed pages.
//! Payload/header nulling is gone — those columns moved to `llm_request_payloads`
//! in the owner bucket.
use std::sync::Arc;
use std::time::Duration;
@@ -31,27 +31,6 @@ pub fn spawn(
_ = tokio::time::sleep(Duration::from_secs(60)) => {}
}
loop {
if let Some(days) = cfg.cleanup_request_payload_after {
match super::null_request_payload(&pool, days).await {
Ok(n) if n > 0 => info!(rows = n, days, "llm_requests: nulled request payload"),
Ok(_) => {}
Err(e) => warn!(error = %e, "llm_requests: null request payload failed"),
}
}
if let Some(days) = cfg.cleanup_response_payload_after {
match super::null_response_payload(&pool, days).await {
Ok(n) if n > 0 => info!(rows = n, days, "llm_requests: nulled response payload"),
Ok(_) => {}
Err(e) => warn!(error = %e, "llm_requests: null response payload failed"),
}
}
if let Some(days) = cfg.cleanup_headers_after {
match super::null_headers(&pool, days).await {
Ok(n) if n > 0 => info!(rows = n, days, "llm_requests: nulled headers"),
Ok(_) => {}
Err(e) => warn!(error = %e, "llm_requests: null headers failed"),
}
}
if let Some(days) = cfg.cleanup_rows_after {
match super::delete_old_rows(&pool, days).await {
Ok(n) if n > 0 => info!(deleted = n, days, "llm_requests: deleted old rows"),
@@ -59,7 +38,7 @@ pub fn spawn(
Err(e) => warn!(error = %e, "llm_requests: delete old rows failed"),
}
}
// VACUUM reclaims pages freed by DELETE/UPDATE NULL.
// VACUUM reclaims pages freed by DELETE.
match sqlx::query("VACUUM").execute(&*pool).await {
Ok(_) => info!("llm_requests: VACUUM complete"),
Err(e) => warn!(error = %e, "llm_requests: VACUUM failed"),
crates/skald-core/src/db/llm_requests/mod.rs
+9 -61
View File
@@ -1,7 +1,9 @@
//! DB operations for the `llm_requests` table.
//! DB operations for the `llm_requests` table (metadata only).
//!
//! Every `chat_with_tools` call is logged here by the
//! [`crate::chatbot::logging::LoggingChatbotClient`] wrapper.
//! Payloads (request/response bodies + headers) live in `llm_request_payloads`
//! in the owner bucket (`{userid}.db`), correlated by `request_id`.
//! Rows are retained for `llm.request_log.retention_days` days (default 14).
use anyhow::Result;
@@ -12,17 +14,11 @@ pub mod cleanup;
// ── Row struct ────────────────────────────────────────────────────────────────
pub struct LlmRequestRow {
pub request_id: Option<String>,
pub user_id: Option<String>,
pub session_id: Option<i64>,
pub stack_id: Option<i64>,
pub model_name: String,
/// Full HTTP request body sent to the provider (compact JSON, no pretty-print).
pub request_json: String,
/// HTTP request headers as a compact JSON object (api-key redacted).
pub request_headers: Option<String>,
/// Full HTTP response body from the provider (compact JSON).
pub response_json: Option<String>,
/// HTTP response headers as a compact JSON object.
pub response_headers: Option<String>,
/// Error message when the HTTP call itself failed (no response available).
pub error_text: Option<String>,
pub input_tokens: Option<i64>,
@@ -40,21 +36,17 @@ pub struct LlmRequestRow {
pub async fn insert(pool: &SqlitePool, row: LlmRequestRow) -> Result<i64> {
let id = sqlx::query_scalar::<_, i64>(
"INSERT INTO llm_requests (
session_id, stack_id, model_name,
request_json, request_headers,
response_json, response_headers,
request_id, user_id, session_id, stack_id, model_name,
error_text, input_tokens, output_tokens, duration_ms,
cache_read_tokens, cache_creation_tokens
) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
RETURNING id",
)
.bind(&row.request_id)
.bind(&row.user_id)
.bind(row.session_id)
.bind(row.stack_id)
.bind(&row.model_name)
.bind(&row.request_json)
.bind(&row.request_headers)
.bind(&row.response_json)
.bind(&row.response_headers)
.bind(&row.error_text)
.bind(row.input_tokens)
.bind(row.output_tokens)
@@ -79,47 +71,3 @@ pub async fn delete_old_rows(pool: &SqlitePool, days: u32) -> Result<u64> {
.rows_affected();
Ok(n)
}
/// Nulls out `request_json` for rows older than `days` days. Returns rows affected.
pub async fn null_request_payload(pool: &SqlitePool, days: u32) -> Result<u64> {
let cutoff = format!("-{days} days");
let n = sqlx::query(
"UPDATE llm_requests SET request_json = '' \
WHERE request_json != '' AND created_at < datetime('now', ?)",
)
.bind(&cutoff)
.execute(pool)
.await?
.rows_affected();
Ok(n)
}
/// Nulls out `response_json` for rows older than `days` days. Returns rows affected.
pub async fn null_response_payload(pool: &SqlitePool, days: u32) -> Result<u64> {
let cutoff = format!("-{days} days");
let n = sqlx::query(
"UPDATE llm_requests SET response_json = NULL \
WHERE response_json IS NOT NULL AND created_at < datetime('now', ?)",
)
.bind(&cutoff)
.execute(pool)
.await?
.rows_affected();
Ok(n)
}
/// Nulls out both header columns for rows older than `days` days. Returns rows affected.
pub async fn null_headers(pool: &SqlitePool, days: u32) -> Result<u64> {
let cutoff = format!("-{days} days");
let n = sqlx::query(
"UPDATE llm_requests \
SET request_headers = NULL, response_headers = NULL \
WHERE (request_headers IS NOT NULL OR response_headers IS NOT NULL) \
AND created_at < datetime('now', ?)",
)
.bind(&cutoff)
.execute(pool)
.await?
.rows_affected();
Ok(n)
}
crates/skald-core/src/db/mod.rs
+24 -4
View File
@@ -10,6 +10,7 @@ pub mod config;
pub mod job_runs;
pub mod known_tools;
pub mod llm_requests;
pub mod llm_request_payloads;
pub mod mcp_events;
pub mod mcp_servers;
pub mod plugins;
@@ -317,16 +318,17 @@ async fn create_registry_tables(pool: &SqlitePool) -> Result<()> {
// decrypting anything: the admin sees how much, when and which model — never
// what was said. `session_id` / `stack_id` are bare integers, not foreign
// keys, precisely because the rows they point at live in another file.
// `user_id` correlates the row with the payload in `{userid}.db`.
// Payloads (request/response bodies, headers) live in `llm_request_payloads`
// in the owner bucket — they are conversation content, behind the user key.
sqlx::query(
"CREATE TABLE IF NOT EXISTS llm_requests (
id INTEGER PRIMARY KEY AUTOINCREMENT,
request_id TEXT,
user_id TEXT,
session_id INTEGER,
stack_id INTEGER,
model_name TEXT NOT NULL,
request_json TEXT NOT NULL DEFAULT '',
request_headers TEXT,
response_json TEXT,
response_headers TEXT,
error_text TEXT,
input_tokens INTEGER,
output_tokens INTEGER,
@@ -691,6 +693,23 @@ pub async fn create_owner_tables(pool: &SqlitePool) -> Result<()> {
.execute(pool)
.await?;
// Full request/response payloads for telemetry. Lives in the owner bucket
// (per-user, encrypted) because it is conversation content. Correlated with
// the metadata row in `system.db` via `request_id` (uuid).
sqlx::query(
"CREATE TABLE IF NOT EXISTS llm_request_payloads (
id INTEGER PRIMARY KEY AUTOINCREMENT,
request_id TEXT NOT NULL,
request_json TEXT NOT NULL DEFAULT '',
request_headers TEXT,
response_json TEXT,
response_headers TEXT,
created_at TEXT NOT NULL DEFAULT (datetime('now'))
)",
)
.execute(pool)
.await?;
Ok(())
}
@@ -744,6 +763,7 @@ mod tests {
one("INSERT INTO secrets (key, value) VALUES ('k', 'v')").await.unwrap();
one("INSERT INTO projects (id, name, path) VALUES (1, 'p', '/tmp')").await.unwrap();
one("INSERT INTO project_tickets (project_id, title, job_id) VALUES (1, 't', 1)").await.unwrap();
one("INSERT INTO llm_request_payloads (request_id, request_json) VALUES ('r1', '{}')").await.unwrap();
pool.close().await;
let _ = std::fs::remove_dir_all(&dir);
crates/skald-core/src/db/users.rs
+2
View File
@@ -456,6 +456,8 @@ mod tests {
async fn cleartext_user_round_trips_with_and_without_a_verifier() {
let path = temp_db_path("users-clear");
let pool = crate::db::init_system_pool(&path).await.unwrap();
crate::db::roles::insert(&pool, "children", "Children", "default", None)
.await.unwrap();
insert(&pool, "u-1", "kid", None, "children", &cleartext()).await.unwrap();
insert(&pool, "u-2", "kiosk", None, "children", &Credentials::Cleartext(None)).await.unwrap();