Pulse Contributors Code Frequency Recent Commits

2026-03-19 - 2026-06-19

Period: 3 months

1 day 3 days 1 week 1 month 3 months 6 months 1 year

Overview

7 Active Pull Requests

10 Active Issues

7
Merged Pull Requests 0
Proposed Pull Requests 10
Closed Issues 10
New Issues

Excluding merges, 2 authors have pushed 10 commits to main and 17 commits to all branches. On main, 16 files have changed and there have been 1890 additions and 445 deletions.

7 Pull requests merged by 1 user

Merged #17 feat: rename dry_run to no_inference for all tiers 2026-03-24 07:27:04 +00:00

Merged #18 feat: rename --dry-run to --no-inference in run_benchmark.py 2026-03-24 07:26:44 +00:00

Merged #19 feat: add run_routing_benchmark.py — routing-only benchmark 2026-03-24 07:26:31 +00:00

Merged #13 Fix routing: add Russian tech def patterns to light, strengthen medium smart home 2026-03-24 02:51:17 +00:00

Merged #14 Remove Bifrost: replace test 4 with LiteLLM health check 2026-03-24 02:48:40 +00:00

Merged #11 Fix tier logging: capture actual_tier, fix parse_run_block regex, remove reply_text truncation 2026-03-24 02:44:35 +00:00

Merged #12 Fix benchmark log extraction: first tier match, increase log tail to 300 2026-03-24 02:43:26 +00:00

10 Issues closed from 1 user

Closed #9 Benchmark: smart home commands (medium) mis-routed to light 2026-03-24 02:52:44 +00:00

Closed #3 Fix reply_text[:200] truncation breaking bench keyword matching 2026-03-24 02:52:44 +00:00

Closed #4 Fix actual_tier never updated from "unknown" in run_agent_task 2026-03-24 02:52:44 +00:00

Closed #10 Benchmark: complex tier never triggered — 0% accuracy (40 queries) 2026-03-24 02:52:44 +00:00

Closed #8 Benchmark: light tier over-classified as medium (tech definition queries) 2026-03-24 02:51:17 +00:00

Closed #5 Remove or replace Bifrost test in test_memory.py 2026-03-24 02:48:40 +00:00

Closed #2 Verify [agent] running: log anchor still emitted in new agent.py 2026-03-24 02:46:02 +00:00

Closed #6 Verify POST /chat still accepts {message, chat_id} after agent.py refactor 2026-03-24 02:46:02 +00:00

Closed #1 Fix parse_run_block regex to match new log format 2026-03-24 02:44:35 +00:00

Closed #7 Benchmark: ~50 queries return "?" due to tier= log extraction timeout 2026-03-24 02:43:26 +00:00

10 Issues created by 0 users

Opened #2 Verify [agent] running: log anchor still emitted in new agent.py 2026-03-24 01:56:50 +00:00

Opened #6 Verify POST /chat still accepts {message, chat_id} after agent.py refactor 2026-03-24 01:56:50 +00:00

Opened #5 Remove or replace Bifrost test in test_memory.py 2026-03-24 01:56:50 +00:00

Opened #1 Fix parse_run_block regex to match new log format 2026-03-24 01:56:50 +00:00

Opened #3 Fix reply_text[:200] truncation breaking bench keyword matching 2026-03-24 01:56:50 +00:00

Opened #4 Fix actual_tier never updated from "unknown" in run_agent_task 2026-03-24 01:56:50 +00:00

Opened #7 Benchmark: ~50 queries return "?" due to tier= log extraction timeout 2026-03-24 01:57:56 +00:00

Opened #8 Benchmark: light tier over-classified as medium (tech definition queries) 2026-03-24 01:58:05 +00:00

Opened #9 Benchmark: smart home commands (medium) mis-routed to light 2026-03-24 01:58:18 +00:00

Opened #10 Benchmark: complex tier never triggered — 0% accuracy (40 queries) 2026-03-24 01:58:46 +00:00