 Hermes CI Bot
|
fd9aa7cbc1
|
feat: expand to 36 tests (5 new domains) + cost tracker
新增: 安全(API密钥/供应链)、架构(微服务/技术选型)、故障响应(宕机/post-mortem)、协作(跨团队/代码质量)、成本优化(云成本/预算)
成本追踪: cost-tracker.py 自动记录每次 eval 的 token 消耗和费用
基线: baseline-20260709-v2.json (36/36通过, $0.0090, 32K tokens)
|
2026-07-09 21:15:22 +08:00 |
|
|
Hermes CI Bot
|
5989d39785
|
feat: add eval baseline 2026-07-09
- First baseline snapshot for drift detection
- 16/16 test cases passed
- 0 failures, 0 errors
|
2026-07-09 20:38:41 +08:00 |
|
|
Hermes CI Bot
|
61ed34cf32
|
chore: trigger hook v4
|
2026-07-09 20:26:03 +08:00 |
|
|
Hermes CI Bot
|
8fc3905d7d
|
chore: trigger hook v3
|
2026-07-09 20:25:38 +08:00 |
|
|
Hermes CI Bot
|
9e88e9fb62
|
chore: test webhook with token
|
2026-07-09 20:24:39 +08:00 |
|
|
Hermes CI Bot
|
f035d9dcdc
|
chore: retrigger with correct webhook URL
|
2026-07-09 20:21:07 +08:00 |
|
|
Hermes CI Bot
|
dde4f40ef7
|
chore: retrigger CI
|
2026-07-09 20:20:00 +08:00 |
|
|
Hermes CI Bot
|
c88f26bd85
|
chore: trigger CI
|
2026-07-09 20:19:37 +08:00 |
|
|
Hermes CI Bot
|
1111ad155c
|
docs: add README with eval overview
|
2026-07-09 20:18:24 +08:00 |
|
|
Hermes CI Bot
|
5ea2710ed2
|
feat: initial Hermes CI eval baseline
- promptfoo eval config with 8 test scenarios
- Assertions: contains-any + latency checks
- Woodpecker pipeline: eval-baseline + report steps
- Evaluates Hermes Bot's project management responses
|
2026-07-09 20:14:15 +08:00 |
|