Skip to content

Actions: dzianisv/opencode-plugins

Actions

Prompt Evaluations

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
evals.yml
72 workflow runs
72 workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
Supervisor controls for reflection-3: configurable rubric, retry budget, session goals (engine) Prompt Evaluations #73: Pull request #144 opened by dvashchuk
1m 46s feat/supervisor-mode
feat/supervisor-mode
1m 46s
Install reflection on Claude Code (/plugin) + OpenCode (plugin section); macOS keychain auth; cheaper CI eval Prompt Evaluations #72: Pull request #142 opened by dzianisv
1m 14s feat/cc-opencode-install-and-eval-cost
feat/cc-opencode-install-and-eval-cost
1m 14s
Reflection prompt: premature-stop antipatterns mined from real sessions Prompt Evaluations #71: Pull request #141 synchronize by dzianisv
1m 22s own/140-reflection-antipatterns
own/140-reflection-antipatterns
1m 22s
Reflection prompt: premature-stop antipatterns mined from real sessions Prompt Evaluations #70: Pull request #141 opened by dzianisv
46s own/140-reflection-antipatterns
own/140-reflection-antipatterns
46s
Claude Code reflection plugin + 907-stop classification baseline Prompt Evaluations #69: Pull request #139 synchronize by dzianisv
51s own/137-cc-reflection
own/137-cc-reflection
51s
Claude Code reflection plugin + 907-stop classification baseline Prompt Evaluations #68: Pull request #139 synchronize by dzianisv
43s own/137-cc-reflection
own/137-cc-reflection
43s
Claude Code reflection plugin + 907-stop classification baseline Prompt Evaluations #67: Pull request #139 synchronize by dzianisv
41s own/137-cc-reflection
own/137-cc-reflection
41s
Claude Code reflection plugin + 907-stop classification baseline Prompt Evaluations #66: Pull request #139 opened by dzianisv
49s own/137-cc-reflection
own/137-cc-reflection
49s
Prompt Evaluations Prompt Evaluations #65: Manually run by dzianisv
3m 7s main
main
3m 7s
ci: gate agent eval on azure secrets Prompt Evaluations #64: Commit e29ebc9 pushed by dzianisv
Failure main
main
Failure
Prompt Evaluations Prompt Evaluations #63: Manually run by dzianisv
2m 41s main
main
2m 41s
Prompt Evaluations Prompt Evaluations #62: Manually run by dzianisv
1m 57s main
main
1m 57s
Prompt Evaluations Prompt Evaluations #61: Manually run by dzianisv
44s main
main
44s
Prompt Evaluations Prompt Evaluations #60: Manually run by dzianisv
41s main
main
41s
Prompt Evaluations Prompt Evaluations #59: Manually run by dzianisv
48s main
main
48s
Clarify stuck eval completion criteria Prompt Evaluations #58: Pull request #130 opened by dzianisv
46s fix/stuck-eval-complete-guidance
fix/stuck-eval-complete-guidance
46s
Add greeter.ts with greet function Prompt Evaluations #57: Pull request #127 synchronize by dzianisv
54s add-hello-js
add-hello-js
54s
Add greeter.ts with greet function Prompt Evaluations #56: Pull request #127 opened by dzianisv
55s add-hello-js
add-hello-js
55s
fix(reflection): avoid blocking on user-action noise Prompt Evaluations #55: Pull request #124 synchronize by dzianisv
1m 0s issue-123-reflection-next-steps
issue-123-reflection-next-steps
1m 0s
fix(reflection): avoid blocking on user-action noise Prompt Evaluations #54: Pull request #124 synchronize by dzianisv
58s issue-123-reflection-next-steps
issue-123-reflection-next-steps
58s
fix(reflection): avoid blocking on user-action noise Prompt Evaluations #53: Pull request #124 synchronize by dzianisv
1m 0s issue-123-reflection-next-steps
issue-123-reflection-next-steps
1m 0s
fix(reflection): avoid blocking on user-action noise Prompt Evaluations #52: Pull request #124 opened by dzianisv
58s issue-123-reflection-next-steps
issue-123-reflection-next-steps
58s
fix(reflection): prevent action loops by reducing max attempts and adding loop detection Prompt Evaluations #51: Pull request #114 synchronize by dzianisv
55s issue-80-reflection-loop-prevention
issue-80-reflection-loop-prevention
55s
fix(reflection): detect Plan mode in user-role system-reminder tags Prompt Evaluations #50: Pull request #113 synchronize by dzianisv
56s issue-74-plan-mode-reflection
issue-74-plan-mode-reflection
56s
fix(reflection): tighten routing and loop feedback Prompt Evaluations #49: Pull request #121 opened by dzianisv
1m 6s issue-120-reflection-toast
issue-120-reflection-toast
1m 6s