Commit Graph

Select branches

Hide Pull Requests

fix/benchmark-log-extraction

fix/tier-logging

main

#11

#12

#13

#14

#15

#16

#17

#18

#19

Mono Color

• 887d4b8d90 voice benchmark: rename --dry-run → --no-inference, fix log extraction main alvis 2026-03-24 07:58:05 +00:00
• 4e6d3090c2 Remove benchmark.json from gitignore — dataset is now tracked alvis 2026-03-24 07:53:35 +00:00
• 5b09a99a7f Routing: 100% accuracy on realistic home assistant dataset alvis 2026-03-24 07:53:01 +00:00
• 3fb90ae083 Skip _reply_semaphore in no_inference mode alvis 2026-03-24 07:40:07 +00:00
• 4d37ac65b2 Skip preflight IO (memory/URL/fast-tools) when no_inference=True alvis 2026-03-24 07:37:55 +00:00
• b7d5896076 routing benchmark: 1s strict deadline per query alvis 2026-03-24 07:35:13 +00:00
• fc53632c7b Merge pull request 'feat: rename dry_run to no_inference for all tiers' (#17) from worktree-agent-afc013ce into main alvis 2026-03-24 07:27:04 +00:00
• 47a1166be6 Merge pull request 'feat: rename --dry-run to --no-inference in run_benchmark.py' (#18) from feat/no-inference-benchmark into main alvis 2026-03-24 07:26:44 +00:00
• 74e5b1758d Merge pull request 'feat: add run_routing_benchmark.py — routing-only benchmark' (#19) from feat/routing-benchmark into main alvis 2026-03-24 07:26:31 +00:00
• 0fbdbf3a5e Add run_routing_benchmark.py — dedicated routing-only benchmark alvis 2026-03-24 07:25:16 +00:00
• 77db739819 Rename --dry-run to --no-inference, apply to all tiers in run_benchmark.py alvis 2026-03-24 03:49:09 +00:00
• 9c2f27eed4 Rename dry_run → no_inference, extend to all tiers in agent.py alvis 2026-03-24 03:43:42 +00:00
• a363347ae5 Merge pull request 'Fix routing: add Russian tech def patterns to light, strengthen medium smart home' (#13) from fix/routing-accuracy into main alvis 2026-03-24 02:51:17 +00:00
• 1d2787766e Merge pull request 'Remove Bifrost: replace test 4 with LiteLLM health check' (#14) from fix/remove-bifrost into main alvis 2026-03-24 02:48:40 +00:00
• abf792a2ec Remove Bifrost: replace test 4 with LiteLLM health check alvis 2026-03-24 02:46:01 +00:00
• 537e927146 Fix routing: add Russian tech def patterns to light, strengthen medium smart home alvis 2026-03-24 02:45:42 +00:00
• 186e16284b Merge pull request 'Fix tier logging: capture actual_tier, fix parse_run_block regex, remove reply_text truncation' (#11) from fix/tier-logging into main alvis 2026-03-24 02:44:35 +00:00
• 0b428e4ada Merge pull request 'Fix benchmark log extraction: first tier match, increase log tail to 300' (#12) from fix/benchmark-log-extraction into main alvis 2026-03-24 02:43:26 +00:00
• 98095679be Fix benchmark log extraction: first tier match, increase log tail to 300 fix/benchmark-log-extraction alvis 2026-03-24 02:42:27 +00:00
• 8ef4897869 Fix tier logging: capture actual_tier, fix parse_run_block regex, remove reply_text truncation fix/tier-logging alvis 2026-03-24 02:41:59 +00:00
• 1f5e272600 Switch from Bifrost to LiteLLM; add Matrix channel; update rules Alvis 2026-03-24 02:14:13 +00:00
• 54cb940279 Update docs: add benchmarks/ section, fix complex tier description Alvis 2026-03-24 02:13:14 +00:00
• bd951f943f Move benchmark scripts into benchmarks/ subdir Alvis 2026-03-24 02:02:46 +00:00
• ab68bba935 Add routing benchmark scripts; gitignore dataset and results Alvis 2026-03-24 02:00:17 +00:00
• 3ae1cefbd4 WeatherTool: fetch open-meteo directly, skip LLM for fast tool replies Alvis 2026-03-15 09:42:55 +00:00
• 957360f6ce Restructure CLAUDE.md per official Claude Code recommendations Alvis 2026-03-13 07:19:09 +00:00
• 3ed47b45da Split CLAUDE.md per official Claude Code recommendations Alvis 2026-03-13 07:15:51 +00:00
• eba805f787 Update docs: fast tools, routecheck service, commute tool Alvis 2026-03-13 07:10:30 +00:00
• 32089ed596 Add routecheck service and CommuteTool fast tool Alvis 2026-03-13 07:08:48 +00:00
• d2ca1926f8 WeatherTool: use Russian query for Celsius sources Alvis 2026-03-13 06:25:53 +00:00
• af181ba7ec Rename RealTimeSearchTool → WeatherTool, fetch Balashikha weather via SearXNG Alvis 2026-03-13 05:40:10 +00:00
• f5fc2e9bfb Introduce FastTools: pre-flight classifier + context enrichment Alvis 2026-03-13 05:18:44 +00:00
• 436299f7e2 Add real-time query handling: pre-search enrichment + routing fix Alvis 2026-03-13 05:08:08 +00:00
• 8cd41940f0 Update docs: streaming, CLI container, use_cases tests Alvis 2026-03-12 17:31:36 +00:00
• b04e8a0925 Add Rich token streaming: server SSE + CLI live display + CLI container Alvis 2026-03-12 17:26:52 +00:00
• edc9a96f7a Add use_cases test category as Claude Code skill instructions Alvis 2026-03-12 17:01:13 +00:00
• a35ba83db7 Add use_cases test category with CLI startup test Alvis 2026-03-12 16:10:04 +00:00
• 021104f510 Split monolithic test_pipeline.py into focused integration test scripts Alvis 2026-03-12 16:02:57 +00:00
• 50097d6092 Embed Crawl4AI at all tiers, restore qwen3:4b medium, update docs Alvis 2026-03-12 15:49:34 +00:00
• f9618a9bbf Integrate Bifrost LLM gateway, add test suite, implement memory pipeline Alvis 2026-03-12 13:50:12 +00:00
• ec45d255f0 wiki search people tested pipeline Alvis 2026-03-05 11:22:34 +00:00
• ea77b2308b Add three-tier model routing with VRAM management and benchmark suite Alvis 2026-02-28 17:54:51 +00:00
• 1718d70203 Fix system prompt: agent now correctly handles memory requests Alvis 2026-02-23 05:22:08 +00:00
• 19e2c27976 Switch extraction model to qwen2.5:1.5b, fix mem0migrations dims, update tests Alvis 2026-02-23 05:11:29 +00:00
• 66ab93aa37 Add Adolf architecture doc and integration test script Alvis 2026-02-23 04:52:40 +00:00