lyl2104626211
ed848da6f0
feat: persist Agent Chat Skill selection by session ( #2160 )
...
* feat: persist Agent Chat skill selection by session
* test: satisfy ChatPage mock immutability lint
* fix: preserve implicit Skill state for legacy sessions
* fix: make top-level Skill selection authoritative
* fix: preserve session skills for invalid requests
---------
Co-authored-by: zhulinsen <42829555+ZhuLinsen@users.noreply.github.com >
2026-08-05 23:12:42 +08:00
zhulinsen
2643d47a96
fix: 让 Agent Chat 默认遵循 REPORT_LANGUAGE ( #2102 )
...
* fix: apply report language to agent chat defaults
* fix(review-feedback-2102): Treat null report language as missing and update those
2026-07-26 16:02:42 +08:00
Alfred
4c678850e2
feat: add Claude Code and OpenCode generation backends ( #1850 )
...
Co-authored-by: zhulinsen <42829555+ZhuLinsen@users.noreply.github.com >
2026-06-30 22:33:02 +08:00
Alfred
62adb5c4ee
feat: add Hermes local HTTP generation ( #1824 )
2026-06-28 17:02:17 +08:00
Alfred
1f91024dec
feat: 新增 codex_cli 本地生成后端 Phase2 ( #1769 )
...
* feat: add codex cli generation backend
* fix: harden local CLI backend phase 2
* fix: harden local cli output file handling
* fix: tighten codex cli backend contracts
* fix: support codex cli windows smoke path
* fix: make local cli tests portable on windows
* fix: avoid duplicate codex final output accounting
2026-06-24 20:19:19 +08:00
mumu
916f7dde00
fix: tighten agent skill compatibility ( #787 )
...
* fix: clean up agent skill compatibility
* fix: tighten backtest tool semantics
* docs: record agent backtest tool semantics
* fix: require explicit skill ids for backtest tools
2026-03-20 16:42:01 +08:00
mumu
6bef880465
refactor: align agent skills with mainstream skill bundles ( #780 )
...
* refactor: align agent skills with mainstream skill bundles
* refactor: derive default agent skills from metadata
* fix: harden skill-first compatibility
* docs: clarify strategy-facing skill terminology
* fix: stop implicit bull-trend skill layering
* fix: use bull-trend as the single implicit default skill
* fix: preserve legacy skill config compatibility
* fix: harden skill metadata compatibility
2026-03-20 15:48:31 +08:00
Alfred
216a77f6a2
fix: decouple agent and analysis primary models ( #692 ) ( #741 )
...
* fix #692 : decouple agent and analysis primary model selection
* fix #692 : preserve yaml alias for agent primary model
* docs #692 : sync agent primary model in EN/CHT readmes
2026-03-18 19:08:36 +08:00
LouisHong
ade41b613c
#602 [PR 2] 配置引擎重构与系统 API (Config & API) ( #611 )
...
* feat: complete PR2 config and system API work
* fix(api): align agent model source detection
* fix(agent): collapse legacy fallback deployments
* fix: expose direct env providers in agent model discovery
---------
Co-authored-by: mumu <42829555+ZhuLinsen@users.noreply.github.com >
2026-03-12 20:47:30 +08:00