Commit Graph

Select branches

Hide Pull Requests

copilot/update-env-adapter-documentation

docs/guideline

feat/skill-aware-reflection

fix/claude-backend-clear-last-error

fix/handoff-notask-and-corrupt-snapshot

fix/minimax-optimizer-deployment

main

refactor/reflect-default-base

users/GitHubPolicyService/51be9fd7-b70b-4938-a8ee-3622f17d8046

users/GitHubPolicyService/8ded453c-4b9b-473f-8865-2117f99a82fd

users/GitHubPolicyService/a41a3ce1-e5a1-4e18-810b-cfb8d2d21c29

users/GitHubPolicyService/c90b1514-6d1f-4da6-9662-3b96a06a9fb2

users/GitHubPolicyService/eb4071d7-d09f-411c-a688-a6f89d362a6a

#101

#102

#103

#104

#105

#107

#109

#109

#110

#112

#114

#114

#115

#116

#118

#118

#122

#123

#124

#125

#126

#128

#129

#131

#133

#134

#134

#135

#136

#137

#138

#139

#140

#141

#143

#144

#146

#147

#148

#148

#149

#15

#150

#151

#151

#152

#152

#153

#153

#16

#17

#18

#2

#20

#23

#24

#25

#26

#27

#29

#31

#32

#34

#36

#37

#39

#4

#40

#41

#43

#44

#47

#48

#49

#5

#50

#55

#55

#59

#6

#60

#61

#63

#64

#65

#7

#72

#73

#74

#77

#78

#79

#80

#81

#82

#83

#83

#85

#86

#87

#88

#89

#9

#9

#92

#96

#98

#99

v0.1.0

v0.2.0

Mono Color

• b860a5cf88 Merge pull request #150 from Yif-Yang/test/assert-fractional-degradation-score main Yifan Yang 2026-07-19 01:28:47 +08:00
• 7933f37bf0 test(sleep): assert fractional candidate score Yif-Yang 2026-07-18 17:28:22 +00:00
• 67b67acf5f Merge pull request #149 from harshitnagar22/test/fractional-degradation-gate Yifan Yang 2026-07-19 01:26:25 +08:00
• 4a4d597527 test(sleep): add fractional degradation gate test for partial held-out regression Harshit Nagar 2026-07-18 22:24:30 +05:30
• 8a50db3312 Merge pull request #147 from detailobsessed/feat/devin-handoff-backend Yifan Yang 2026-07-18 01:01:59 +08:00
• 195d95e00c feat(devin): expose handoff backend in MCP server enum (#3) Ismar 2026-07-16 15:19:47 +02:00
• d2670205d1 Merge pull request #146 from Yif-Yang/fix/codex-token-tracker-isolation Yifan Yang 2026-07-16 19:03:02 +09:00
• 74ff263608 fix(model): isolate Codex token tracking Yif-Yang 2026-07-16 10:02:21 +00:00
• 3e3df8895e Merge pull request #112 from TheGameVIX/agent/codex-exec-optimizer-main Yifan Yang 2026-07-16 18:57:47 +09:00
• 0d8839778c Merge pull request #101 from SparshGarg999/fix/46-windows-support-codex Yifan Yang 2026-07-16 18:57:15 +09:00
• 0b94f890a0 fix(codex): support exec optimizer backend TheGameVIX 2026-07-08 13:49:55 -04:00
• 7c7fdfcd6c fix(windows): resolve control flow and path quoting in scheduler task execution Sparsh :) 2026-07-15 14:54:27 +05:30
• 57333f3406 Merge pull request #143 from Yif-Yang/draft/technical-blog-sar-review Yifan Yang 2026-07-15 04:12:07 +09:00
• a44566aeb8 docs: clarify technical blog structure and SAR Yif-Yang 2026-07-14 18:43:56 +00:00
• 9babe37944 Merge pull request #140 from Yif-Yang/docs/technical-blog-gating-reflection Yifan Yang 2026-07-15 03:14:20 +09:00
• a12072241d docs: launch SkillOpt Technical Blog Yif-Yang 2026-07-14 18:12:58 +00:00
• a49d0eb1b9 Merge pull request #139 from Yif-Yang/docs/sync-post-v0.2 Yifan Yang 2026-07-15 02:16:18 +09:00
• f31bf8c06b docs: sync documentation with post-v0.2 changes Yif-Yang 2026-07-14 17:11:40 +00:00
• efb30b4bcc Merge pull request #138 from Yif-Yang/fix/sleep-openai-compat-safety Yifan Yang 2026-07-14 18:17:58 +09:00
• 8b39394c88 fix(sleep): harden OpenAI compatibility boundaries Yif-Yang 2026-07-14 09:17:18 +00:00
• be2184660a Merge pull request #129 from Alphaxalchemy/feat/openai-compatible-endpoints Yifan Yang 2026-07-14 18:10:17 +09:00
• 940c3cd4ec Merge pull request #137 from Yif-Yang/fix/claude-tempdir-cleanup Yifan Yang 2026-07-14 17:50:10 +09:00
• 42270f7fa4 Merge pull request #136 from Yif-Yang/fix/json-array-scan-linear Yifan Yang 2026-07-14 17:50:07 +09:00
• 6a193ffd78 fix(claude): use cleanup-tolerant temporary directory Yif-Yang 2026-07-14 08:46:54 +00:00
• 48e4c66827 perf(json): keep array scan linear on malformed output Yif-Yang 2026-07-14 08:46:54 +00:00
• 1b64b000fb Merge pull request #135 from nankingjing/fix/issue-117-wheel-md-and-tempdir Yifan Yang 2026-07-14 17:41:55 +09:00
• 7191f1cb1f Merge pull request #103 from zixuanguo786-ctrl/codex/robust-json-array-extraction Yifan Yang 2026-07-14 17:41:52 +09:00
• 7bf9ecbec6 Merge pull request #115 from nankingjing/contrib/add-openai-compatible-backend Yifan Yang 2026-07-14 17:41:49 +09:00
• 2ffa73410e Merge pull request #105 from zixuanguo786-ctrl/codex/reject-duplicate-searchqa-manifest-ids Yifan Yang 2026-07-14 17:41:45 +09:00
• c2992b96a6 Merge pull request #104 from zixuanguo786-ctrl/codex/preserve-fractional-hard-score Yifan Yang 2026-07-14 17:41:42 +09:00
• 4ff77b71ff fix(sleep): address review — CLI choice, auth guard, provider-neutral kwargs, tests Alphaxalchemy 2026-07-14 01:22:19 -06:00
• df5bf20f09 Fix #117: include .md prompt files in wheel + handle Windows temp-dir cleanup nankingjing 2026-07-14 11:17:19 +08:00
• ddc35b339d Fix array extraction after unmatched brace Ziiii 2026-07-14 09:35:42 +08:00
• 45ff88a20c test(model): cover OpenAI-compatible backend integration nankingjing 2026-07-14 09:21:11 +08:00
• e452761231 docs(new-backend): document the built-in openai_compatible backend 黄云龙 2026-07-09 23:28:43 +08:00
• 608757a73f feat(model): route optimizer/target calls to the openai_compatible backend 黄云龙 2026-07-09 23:28:41 +08:00
• 9dc43fccc4 feat(model): accept openai_compatible as optimizer/target backend 黄云龙 2026-07-09 23:28:40 +08:00
• 3656f1cb54 feat(model): register openai_compatible backend (aliases + default model) 黄云龙 2026-07-09 23:28:39 +08:00
• 84ea713a71 feat(model): add OpenAI-compatible generic backend for any OpenAI-compatible API 黄云龙 2026-07-09 23:28:38 +08:00
• 50fed2958b Merge pull request #133 from Yif-Yang/fix/scheduler-preserve-annealing-contract Yifan Yang 2026-07-14 02:01:48 +09:00
• a0b6db59f8 fix(scheduler): preserve existing annealing contract Yif-Yang 2026-07-13 16:57:07 +00:00
• e7665f8f5e Merge pull request #123 from nankingjing/test-scheduler-core Yifan Yang 2026-07-14 01:54:24 +09:00
• ed0770dd38 Merge pull request #131 from AKhozya/feat/preferences-cli-wiring Yifan Yang 2026-07-14 01:54:05 +09:00
• daf3035429 test(scheduler): update sequence expectation to match consistent endpoint formula 黄云龙 2026-07-14 00:45:22 +08:00
• 9f9f87c064 fix(scheduler): use consistent (step-1)/(total_steps-1) endpoint formula 黄云龙 2026-07-14 00:45:12 +08:00
• 3b0af4668c feat: wire preferences through run cycle into reflect prior AKhozya 2026-07-07 11:31:29 +01:00
• 79d6117f6f fix: address PR reviews, add scheduler Windows tasks and Pester coverage Sparsh :) 2026-07-13 21:20:30 +05:30
• 3c45db3a90 feat(codex): add Windows support and compatibility for Codex plugin Sparsh :) 2026-07-05 17:23:51 +05:30
• 25b0f39405 Merge pull request #107 from ichoosetoaccept/fix/plugin-pip-fallback Yifan Yang 2026-07-14 00:36:17 +09:00
• 340a4c870f fix(minimax): honour OPTIMIZER_DEPLOYMENT for optimizer-role calls fix/minimax-optimizer-deployment Yif Yang 2026-07-13 06:35:38 +00:00
• af33f6c338 feat(sleep): support OpenAI-compatible endpoints in azure_openai backend Alphaxalchemy 2026-07-12 21:03:48 -06:00
• 83e3be9298 fix(sleep): handoff no-task cleanup + corrupt tasks.json fallback fix/handoff-notask-and-corrupt-snapshot Yif Yang 2026-07-12 16:36:23 +00:00
• fad8fdb01f fix(sleep): reset ClaudeCliBackend.last_call_error at each call start fix/claude-backend-clear-last-error Yif Yang 2026-07-12 16:33:18 +00:00
• 49a5b617c0 fix(gate): resolve issue #100 (#102) Sparsh :) 2026-07-12 21:57:13 +05:30
• da99301210 fix(harvest): exclude sub-agent transcripts and plugin noise from task mining (#99) codeL1985 2026-07-13 00:27:05 +08:00
• 19d98ea01c fix(model): route chat_optimizer through minimax_chat (not just chat_target) (#116) Jay C 2026-07-12 12:25:55 -04:00
• 46e8e800bc fix(qwen): support reasoning-model params (max_completion_tokens, omit temperature) (#128) Chirag Singhal 2026-07-12 21:54:40 +05:30
• b309723baa feat(sleep): add handoff backend — session-executed model calls, no API subprocess (#125) dimitarvdenev 2026-07-12 18:23:53 +02:00
• 7df49656d1 fix(skillopt-sleep): surface Claude CLI spawn failures instead of silent zero scores (#126) ClumsyLucid 2026-07-13 00:23:10 +08:00
• df94a91ddc fix: make ClaudeCliBackend work on Windows (.cmd shim resolution + argv length) (#98) codeL1985 2026-07-13 00:22:14 +08:00
• cd8034c2db test(sleep): assert scores and gate_action in verifier tests (closes #94) (#96) Tanmay Garg 2026-07-12 21:50:30 +05:30
• 352cbc3445 fix(config): read YAML config files as UTF-8 (#124) 黄云龙 2026-07-13 00:19:59 +08:00
• 8687566792 test(gate): add unit tests for evaluation gate decision function (#122) 黄云龙 2026-07-13 00:19:56 +08:00
• 3c565a7f84 test: add unit tests for skillopt.optimizer.scheduler 黄云龙 2026-07-11 15:06:11 +08:00
• ce55241a89 fix(plugin): fall back to pip/uv-installed skillopt-sleep in run-sleep.sh Ismar 2026-07-06 14:19:52 +02:00
• 08916747ef Reject overlapping SearchQA manifest ids Ziiii 2026-07-06 15:42:15 +08:00
• 0c30b778fb Preserve continuous rollout hard scores Ziiii 2026-07-06 15:42:07 +08:00
• bf85781ffb Avoid ambiguous JSON array extraction Ziiii 2026-07-06 15:42:01 +08:00
• e4ea6a6771 chore(release): v0.2.0 v0.2.0 CharlesYang030 2026-07-02 22:11:10 +08:00
• 5487e2c426 fix(skillopt-sleep): redact secrets before persisting cycle diagnostics Yif Yang 2026-06-30 19:47:36 +00:00
• b9142bad24 fix(skillopt-sleep): surface codex auth/model/version failures instead of silently scoring 0 (#92) Yifan Yang 2026-07-01 03:20:08 +08:00
• 95a9e959fe test(sleep): add verifier-discipline stress test for the validation gate (#87) Yifan Yang 2026-07-01 02:40:24 +08:00
• 680dd28f5a fix(tests): move TestVerifierDiscipline above main block Tanmay9223 2026-06-30 13:05:01 +05:30
• fccc21f3f6 test(sleep): add verifier-discipline stress test (closes #67) Tanmay9223 2026-06-24 23:54:48 +05:30
• 6849e609a3 feat(eval): add missing minimax backend configuration Yifan Yang 2026-06-23 20:31:39 +08:00
• 9fa0716c72 fix(skillopt-sleep): also surface codex failures on the tool-call rollout path Daniel Martinez 2026-06-27 23:56:11 -05:00
• 9fcf5868c3 fix(skillopt-sleep): surface codex auth/model/version failures instead of silently scoring 0 Daniel Martinez 2026-06-27 22:23:19 -05:00
• 9969a8f393 Add Devin plugin (plugins/devin): MCP server + ATIF-v1.7 harvest (#88) Yifan Yang 2026-06-26 11:04:23 +08:00
• 26e5338def Update citation from @misc to @article format Yif Yang 2026-06-26 02:54:46 +00:00
• 1a70e4c9cd devin harvest: space turns >=5s so single-turn sessions aren't dropped khashayar 2026-06-25 22:03:15 +02:00
• 9799c41461 devin plugin: full schema/tool parity with plugins/copilot khashayar 2026-06-25 21:56:42 +02:00
• e51eb7c4be devin plugin: expand ~ in CLAUDE_HOME from env + add tests & ATIF fixture khashayar 2026-06-25 21:49:21 +02:00
• 99ccb93945 fix(eval-only): configure qwen_chat/minimax backends so local LLM endpoints work (#85) Yifan Yang 2026-06-26 02:55:18 +08:00
• 9de9220214 docs(sleep): add cross-model scaling results (nano +11.9) and hyperparam ablation (#89) Yifan Yang 2026-06-26 01:40:58 +08:00
• bec23ed020 Add Devin plugin (plugins/devin): MCP server + ATIF-v1.7 harvest khashayar 2026-06-25 10:42:52 +02:00
• 8559308361 fix(eval-only): call configure_qwen_chat so itslocal LLM endpoints can be used Gergely Imreh 2026-06-24 15:00:56 +08:00
• 2d7e37a395 fix(json_utils): reject prose pseudo-JSON in single quotes/backticks (#82) Yifan Yang 2026-06-23 20:31:39 +08:00
• baad64a3b9 docs(readme): remove Acknowledgements section (#81) Yifan Yang 2026-06-23 19:13:16 +08:00
• c2e47c50fb docs(readme): acknowledge community contributor @samuelgoofus-boop (#80) Yifan Yang 2026-06-23 19:03:30 +08:00
• 14c045f04f Windows robustness for claude/codex backends (+ hardened JSON fallback) (#79) Yifan Yang 2026-06-23 19:00:23 +08:00
• 2841f82428 Fix ALFWorld gamefile paths relative to ALFWORLD_DATA carpedkm 2026-06-23 10:32:38 +00:00
• 64c6dda105 Merge pull request #78 from Yif-Yang/main Yifan Yang 2026-06-23 16:52:42 +08:00
• c98eac18c7 docs(readme): add Trendshift daily/weekly badges (#1) Yifan Yang 2026-06-23 16:50:47 +08:00
• fc1f827f07 Merge pull request #74 from Yif-Yang/fix/python-path-and-lookback Yifan Yang 2026-06-20 22:26:43 +08:00
• 01b3e01804 fix: use None default for --lookback-hours to distinguish omitted vs 0 carpedkm 2026-06-20 14:23:17 +00:00
• 01075c90d3 fix: address codex round 2 — revert harvest break + allow lookback 0 carpedkm 2026-06-20 14:21:18 +00:00
• 6cc1cd2e95 fix: address codex review — use clock for cutoff + early-exit harvest carpedkm 2026-06-20 14:11:58 +00:00
• 889238b234 fix: add SKILLOPT_SLEEP_PYTHON override + lookback_hours first-run fallback carpedkm 2026-06-20 14:07:50 +00:00
• b5a1c2b317 Merge pull request #73 from Yif-Yang/fix/bare-subscription-auth Yifan Yang 2026-06-20 21:46:09 +08:00
• 552ddefd74 fix: narrow CLI error markers to avoid false positives carpedkm 2026-06-20 13:32:43 +00:00