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.

Co-Authored-By: Claude Sonnet 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_017ic4b4VQVEJWetTT1dYzyJ
2026-10-29 06:10:22 +00:00
parent aa8b1604ed
commit 6d792f00e0
48 changed files with 2093 additions and 0 deletions
@@ -0,0 +1,15 @@
+# The simulated provider: same input, same outcome
+
+Two separate provider instances, same seed, tickets 1..20,000, one call each: identical outcome lists = true
+
+Outcome of the first call per ticket (the plan: 1.5% 429, 0.5% 503, 0.3% never valid, 1.2% invalid on the first reply only):
+  429                                                  304   1.52%
+  503                                                   93   0.47%
+  bad JSON: category not in schema                      76   0.38%
+  bad JSON: missing field                               77   0.39%
+  bad JSON: not JSON                                   137   0.69%
+  valid JSON                                        17,361  86.81%
+  valid JSON (in a markdown fence, stripped)         1,952   9.76%
+
+Quota check: quota 100 calls/second, 300 calls fired back to back -> 201 rejected with 429 (quota rejections plus any injected 429)
+Every number above is a property of the TEST PLAN, not a measurement of any provider.