solahqb

0 Followers · 0 Following

• Joined on 2026-06-26

Repositories

2

Projects Packages Public Activity Starred Repositories

solahqb pushed to main at solahqb/AgentEvalTool 2026-07-29 03:23:32 +00:00

770d260750 feat(report): compare requires same scenario version (ticket 05)

0a47260237 feat(run): snapshot scenario version at run creation (ticket 04)

43e05ee38d feat(scenario): system-maintained syllabus version (ticket 03)

8a526599ab feat(report): annotate connectivity cases and add judged pass rate (ticket 02)

5dd1bc8535 feat(engine): expectations now additive with explicit rules (ticket 01)

Compare 5 commits »

solahqb pushed to main at solahqb/AgentEvalTool 2026-07-29 02:16:49 +00:00

2dcf415940 docs(v0.5): add spec and tracer-bullet tickets for judgement semantics & scenario versioning

solahqb pushed to main at solahqb/AgentEvalTool 2026-07-28 13:47:01 +00:00

e33922c3fe docs(domain): add domain glossary CONTEXT.md and first ADRs

solahqb pushed to main at solahqb/AgentEvalTool 2026-07-28 11:54:26 +00:00

c2bc56effd fix(deploy): use npmmirror registry in volcengine-102 Dockerfile

solahqb pushed to main at solahqb/AgentEvalTool 2026-07-28 09:41:34 +00:00

595409487b docs(release): v0.4「联」发布说明与里程碑收尾

9c564b575e feat(frontend): v0.4 login page, dashboard rebuild, reports UX, keep-alive refresh

739d586aec feat(backend): v0.4 triggered_by tracking, login gate, compare guard, dashboard stats

Compare 3 commits »

solahqb pushed to main at solahqb/AgentEvalTool 2026-07-27 08:51:56 +00:00

92f98c3af7 docs(release): add v0.3 release notes and minimal CI baseline

solahqb pushed to main at solahqb/AgentEvalTool 2026-07-20 09:26:03 +00:00

f1eb123dd1 fix: use GATEWAY_MODE=local for openclaw-eval

solahqb pushed to main at solahqb/AgentEvalTool 2026-07-20 09:24:46 +00:00

26a36f5bdb fix: add OPENCLAW_ALLOW_UNCONFIGURED env var

solahqb pushed to main at solahqb/AgentEvalTool 2026-07-20 09:21:55 +00:00

baba638fd5 fix: use private registry for openclaw image

solahqb pushed to main at solahqb/AgentEvalTool 2026-07-20 07:53:18 +00:00

d0831684ec fix(deploy): stamp head instead of upgrade to avoid duplicate column

solahqb pushed to main at solahqb/AgentEvalTool 2026-07-20 07:50:35 +00:00

d970a9c06a fix(deploy): init_db before alembic to create base tables

solahqb pushed to main at solahqb/AgentEvalTool 2026-07-20 07:37:43 +00:00

c6700e9c89 fix(deploy): remove COPY data/scenarios (gitignored), use mkdir instead

solahqb pushed to main at solahqb/AgentEvalTool 2026-07-20 07:33:54 +00:00

5b1c88065b feat(deploy): add volcengine-102 production deployment

solahqb pushed to main at solahqb/AgentEvalTool 2026-07-17 13:41:57 +00:00

affbf60945 feat(models): add model capability metadata

solahqb pushed to main at solahqb/AgentEvalTool 2026-07-17 13:18:37 +00:00

b3c6c1fa7a docs: add repository agent guidelines

solahqb pushed to main at solahqb/AgentEvalTool 2026-07-17 12:58:42 +00:00

cc79d3a625 feat(models): support mainstream model protocols

solahqb pushed to main at solahqb/AgentEvalTool 2026-07-17 12:35:00 +00:00

457dfed252 fix(frontend): refresh scenario model references

solahqb pushed to main at solahqb/AgentEvalTool 2026-07-17 12:03:00 +00:00

470ff5875f feat(models): add centralized model configuration

solahqb pushed to main at solahqb/AgentEvalTool 2026-07-17 10:14:03 +00:00

9293f9e842 feat(files): improve category and location layout

solahqb pushed to main at solahqb/AgentEvalTool 2026-07-17 09:41:35 +00:00

d7514f4e65 refactor(files): harden storage and split frontend