evalgate · Workflow runs · AgentPostmortem/Evalgate · GitHub

Actions

evalgate

Actions

Loading...
Loading

44 workflow runs

44 workflow runs

feat: add word-count scorer evalgate #48: Pull request #57 synchronize by royalpinto007

13s sharadvc:feat/word-count-scorer

sharadvc:feat/word-count-scorer

13s

feat: add refusal scorer evalgate #47: Pull request #56 synchronize by royalpinto007

13s sharadvc:feat/refusal-scorer

sharadvc:feat/refusal-scorer

13s

feat: add word-count scorer evalgate #46: Pull request #57 synchronize by royalpinto007

14s sharadvc:feat/word-count-scorer

sharadvc:feat/word-count-scorer

14s

feat: add tool-call scorer evalgate #45: Pull request #55 synchronize by royalpinto007

12s sharadvc:feat/tool-call-scorer

sharadvc:feat/tool-call-scorer

12s

feat: add word-count scorer evalgate #44: Pull request #57 opened by sharadvc

12s sharadvc:feat/word-count-scorer

sharadvc:feat/word-count-scorer

12s

feat: add refusal scorer evalgate #43: Pull request #56 opened by sharadvc

13s sharadvc:feat/refusal-scorer

sharadvc:feat/refusal-scorer

13s

feat: add tool-call scorer evalgate #42: Pull request #55 opened by sharadvc

13s sharadvc:feat/tool-call-scorer

sharadvc:feat/tool-call-scorer

13s

feat: add json-nonempty scorer evalgate #41: Pull request #54 opened by sharadvc

13s sharadvc:feat/json-nonempty-scorer

sharadvc:feat/json-nonempty-scorer

13s

docs: add example output to README quickstart evalgate #40: Pull request #53 opened by sharadvc

12s sharadvc:cursor/readme-quickstart-output-37d6

sharadvc:cursor/readme-quickstart-output-37d6

12s

docs: document missing flags in CLI help evalgate #39: Pull request #52 opened by sharadvc

15s sharadvc:cursor/cli-help-missing-flags-f9d9

sharadvc:cursor/cli-help-missing-flags-f9d9

15s

fix: honor --tags and --concurrency in baseline and compare evalgate #38: Pull request #51 opened by sharadvc

12s sharadvc:cursor/fix-baseline-compare-tags-465c

sharadvc:cursor/fix-baseline-compare-tags-465c

12s

fix: fail cost scorer when costUsd is undefined evalgate #37: Pull request #50 opened by sharadvc

12s sharadvc:cursor/fix-cost-undefined-67f4

sharadvc:cursor/fix-cost-undefined-67f4

12s

fix: reject empty prompts and invalid messages in suite validation evalgate #36: Pull request #49 opened by sharadvc

14s sharadvc:cursor/suite-validation-empty-prompt-27-ebda

sharadvc:cursor/suite-validation-empty-prompt-27-ebda

14s

fix: handle invalid regex in rubric criteria without crashing evalgate #35: Pull request #48 opened by sharadvc

13s sharadvc:cursor/fix-rubric-invalid-regex-22b4

sharadvc:cursor/fix-rubric-invalid-regex-22b4

13s

fix: reject invalid numeric CLI flags instead of silent fallback evalgate #34: Pull request #47 opened by sharadvc

12s sharadvc:cursor/fix-invalid-numeric-cli-3ca6

sharadvc:cursor/fix-invalid-numeric-cli-3ca6

12s

fix: reject non-finite scorer weights evalgate #33: Pull request #46 opened by sharadvc

12s sharadvc:cursor/fix-infinity-weight-9911

sharadvc:cursor/fix-infinity-weight-9911

12s

fix: normalize string tags so --tags filtering works evalgate #32: Pull request #45 opened by sharadvc

14s sharadvc:cursor/fix-string-tags-1119

sharadvc:cursor/fix-string-tags-1119

14s

fix: reject llm-judge scores outside [0, 1] evalgate #31: Pull request #44 opened by sharadvc

12s sharadvc:cursor/fix-llm-judge-unclamped-32a7

sharadvc:cursor/fix-llm-judge-unclamped-32a7

12s

fix: reject out-of-range embedding-similarity thresholds evalgate #30: Pull request #43 opened by sharadvc

12s sharadvc:cursor/fix-embedding-threshold-e6f4

sharadvc:cursor/fix-embedding-threshold-e6f4

12s

fix: reject negative or NaN compareRuns tolerance evalgate #29: Pull request #42 opened by sharadvc

13s sharadvc:cursor/fix-compare-tolerance-8734

sharadvc:cursor/fix-compare-tolerance-8734

13s

fix: empty contains needle should fail, not always pass evalgate #28: Pull request #41 opened by sharadvc

11s sharadvc:cursor/fix-contains-empty-needle-fe1c

sharadvc:cursor/fix-contains-empty-needle-fe1c

11s

Fix empty filtered runs passing evalgate #27: Pull request #32 opened by vsolano9

13s vsolano9:fix-empty-filter-run

vsolano9:fix-empty-filter-run

13s

feat(suite): expose provider sampling options evalgate #26: Pull request #23 synchronize by royalpinto007

14s vsolano9:feat-17-sampling-options

vsolano9:feat-17-sampling-options

14s

feat(suite): expose provider sampling options evalgate #25: Pull request #23 reopened by royalpinto007

13s vsolano9:feat-17-sampling-options

vsolano9:feat-17-sampling-options

13s

fix: Honor trim:false in exact-match normalize evalgate #24: Pull request #25 reopened by royalpinto007

11s VedantMadane:fix/issue-9

VedantMadane:fix/issue-9

11s