2 Commits

Author	SHA1	Message	Date
alvis	8ef4897869	Fix tier logging: capture actual_tier, fix parse_run_block regex, remove reply_text truncation ... - Add tier_capture param to _run_agent_pipeline; append tier after determination - Capture actual_tier in run_agent_task from tier_capture list - Log tier in replied-in line: [agent] replied in Xs tier=Y - Remove reply_text[:200] truncation (was breaking benchmark keyword matching) - Update parse_run_block regex to match new log format; llm/send fields now None Fixes #1, #3, #4 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-03-24 02:41:59 +00:00
Alvis	021104f510	Split monolithic test_pipeline.py into focused integration test scripts ... - common.py: shared config, URL constants, benchmark questions, all helpers (get, post_json, check_sse, qdrant_count, fetch_logs, parse_run_block, wait_for, etc.) - test_health.py: service health checks (deepagents, bifrost, GPU/CPU Ollama, Qdrant, SearXNG) - test_memory.py: name store/recall pipeline, memory benchmark (5 facts + 10 recalls), dedup test - test_routing.py: easy/medium/hard tier routing benchmarks with --easy/medium/hard-only flags - Removed test_pipeline.py Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-03-12 16:02:57 +00:00