8 Commits
Author SHA1 Message Date
chenmingxuan 6b2c0f199d fix(deps): upgrade OpenAI stack and resolve dependency vulnerabilities 2026-10-28 11:22:04 +08:00
chenmingxuan fac4ccb760 feat: prepare 2.2.0 with UI and execution fixes
Add dark theme, richer Markdown and readable plugin results.
Improve Android input evidence, response integrity and diagnostics.
Unify lifecycle, guidance receipts and evidence sources across clients.
Keep direct action dispatch without an added AI quota approval layer.
Align version metadata at 2.2.0 and bundle Helper 1.2.2.

Validation: 3063 backend tests before the version bump; 44 after.
Frontend: 317 tests and production build passed.
2026-10-26 00:44:13 +08:00
chenmingxuan e1ea099592 feat: add official Codex skill and harden task execution
Install and update artemis-use with task diagnostics and plugin guidance. Preserve cross-device file receipts, review canonical reports, guard stage transitions and reduce small history summaries. Improve exploration lifecycle, request recovery and browser live connections.
2026-10-18 14:18:37 +08:00
chenmingxuan 621f30e437 fix: preserve exploration tool history and cap context budget 2026-10-16 19:05:35 +08:00
chenmingxuan d31eb2a19d feat: add tool-call fallback and resilient batch exports 2026-09-29 19:53:20 +08:00
chenmingxuan 7b1a0755e2 feat: enable full AI automation and safe startup updates 2026-09-22 23:50:03 +08:00
somew1nd 2acdeba8c5 feat(reliability): centralize retry failure classification 2026-09-01 11:51:29 -07:00
somew1nd cbe8f4f0c6 feat: harden agent verification and runtime contracts
Introduce two-gate checker settlement, explicit graph visibility and checkpoints, structured LLM reliability, centralized action specifications, and corresponding tests and design documentation.
2026-08-31 20:42:24 -07:00