7ec45642eb
Some checks failed
PR Checklist / pr-checklist (pull_request) Failing after 1m27s
Implements the Ansible Infrastructure as Code story from KT 2026-04-08. One canonical Ansible playbook defines: - Deadman switch (snapshot good config on health, rollback+restart on death) - Golden state config deployment (Anthropic BANNED, Kimi→Gemini→Ollama) - Cron schedule (source-controlled, no manual crontab edits) - Agent startup sequence (pull→validate→start→verify) - request_log telemetry table (every inference call logged) - Thin config pattern (immutable local pointer to upstream) - Gitea webhook handler (deploy on merge) - Config validator (rejects banned providers) Fleet inventory: Timmy (Mac), Allegro (VPS), Bezalel (VPS), Ezra (VPS) Roles: wizard_base, golden_state, deadman_switch, request_log, cron_manager Addresses: timmy-config #442, #443, #444, #445, #446 References: KT Final 2026-04-08 P2, KT Bezalel 2026-04-08 #1-#5
65 lines
2.4 KiB
SQL
65 lines
2.4 KiB
SQL
-- =============================================================================
|
|
-- request_log — Inference Telemetry Table
|
|
-- =============================================================================
|
|
-- Every agent writes to this table BEFORE and AFTER every inference call.
|
|
-- No exceptions. No summarizing. No describing what you would log.
|
|
-- Actually write the row.
|
|
--
|
|
-- Source: KT Bezalel Architecture Session 2026-04-08
|
|
-- =============================================================================
|
|
|
|
CREATE TABLE IF NOT EXISTS request_log (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
timestamp TEXT NOT NULL DEFAULT (datetime('now')),
|
|
agent_name TEXT NOT NULL,
|
|
provider TEXT NOT NULL,
|
|
model TEXT NOT NULL,
|
|
endpoint TEXT NOT NULL,
|
|
tokens_in INTEGER,
|
|
tokens_out INTEGER,
|
|
latency_ms INTEGER,
|
|
status TEXT NOT NULL, -- 'success', 'error', 'timeout', 'fallback'
|
|
error_message TEXT
|
|
);
|
|
|
|
-- Index for common queries
|
|
CREATE INDEX IF NOT EXISTS idx_request_log_agent
|
|
ON request_log (agent_name, timestamp);
|
|
|
|
CREATE INDEX IF NOT EXISTS idx_request_log_provider
|
|
ON request_log (provider, timestamp);
|
|
|
|
CREATE INDEX IF NOT EXISTS idx_request_log_status
|
|
ON request_log (status, timestamp);
|
|
|
|
-- View: recent activity per agent (last hour)
|
|
CREATE VIEW IF NOT EXISTS v_recent_activity AS
|
|
SELECT
|
|
agent_name,
|
|
provider,
|
|
model,
|
|
status,
|
|
COUNT(*) as call_count,
|
|
AVG(latency_ms) as avg_latency_ms,
|
|
SUM(tokens_in) as total_tokens_in,
|
|
SUM(tokens_out) as total_tokens_out
|
|
FROM request_log
|
|
WHERE timestamp > datetime('now', '-1 hour')
|
|
GROUP BY agent_name, provider, model, status;
|
|
|
|
-- View: provider reliability (last 24 hours)
|
|
CREATE VIEW IF NOT EXISTS v_provider_reliability AS
|
|
SELECT
|
|
provider,
|
|
model,
|
|
COUNT(*) as total_calls,
|
|
SUM(CASE WHEN status = 'success' THEN 1 ELSE 0 END) as successes,
|
|
SUM(CASE WHEN status = 'error' THEN 1 ELSE 0 END) as errors,
|
|
SUM(CASE WHEN status = 'timeout' THEN 1 ELSE 0 END) as timeouts,
|
|
SUM(CASE WHEN status = 'fallback' THEN 1 ELSE 0 END) as fallbacks,
|
|
ROUND(100.0 * SUM(CASE WHEN status = 'success' THEN 1 ELSE 0 END) / COUNT(*), 1) as success_rate,
|
|
AVG(latency_ms) as avg_latency_ms
|
|
FROM request_log
|
|
WHERE timestamp > datetime('now', '-24 hours')
|
|
GROUP BY provider, model;
|