asmhatre/spring-ai
1
0
Fork 0
Code Activity

Add batch-llm module: 100,000 synthetic tickets classified by a ChatClient in a Spring Batch 6 chunk step with Resilience4j rate limiting and retry, skip-and-record for malformed JSON, restart after kill -9 in a second JVM, and a per-chunk cost ledger. The model is a deterministic simulated ChatModel; prices are configurable placeholders. No provider called.

Browse Source 
Co-Authored-By: Claude Sonnet 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_017ic4b4VQVEJWetTT1dYzyJ
This commit is contained in:
asmhatre
2026-10-29 06:10:22 +00:00
co-authored by Claude Sonnet 5.5
parent aa8b1604ed
commit 6d792f00e0
48 changed files with 2093 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
batch-llm/scripts/run-all.sh
Executable
+12
View File
@@ -0,0 +1,12 @@
#!/usr/bin/env bash
# Regenerates every file under output/. No API key, no Docker, no network beyond Maven Central.
# Takes several minutes on a busy 2-vCPU machine: the 100,000-ticket job runs twice (once clean,
# once crashed and resumed). TICKETS=20000 scripts/run-all.sh gives a quicker, smaller version.
set -euo pipefail
source "$(dirname "$0")/common.sh"
rm -rf output target/test-db target/test-meters
mvn -B -q -T1 package 2>&1 | grep -E "Tests run:|BUILD|FAIL|ERROR" || true
scripts/run-clean.sh
scripts/crash-restart.sh
scripts/compare.sh
ls output