Commit Graph

23 Commits

Author SHA1 Message Date
Haoran
711249e297 fix: build task dependencies in two phases 2026-08-19 01:35:08 +08:00
Haoran
b6b5f331ab fix: preserve only unseen tool results 2026-08-16 17:32:53 +08:00
123456wda
c77cd7e813 fix: normalize generated content newlines 2026-08-15 21:15:27 +08:00
Haoran
168fff86dd Fix empty tool-use response handling 2026-08-15 00:03:45 +08:00
Haoran
acdeacc47a Fix skill frontmatter parsing 2026-08-14 23:14:19 +08:00
Haoran
7e2f2fd99b refactor: streamline the course to 17 lessons 2026-08-12 03:02:42 +08:00
Haoran
ab35e59672 Refine course progression and runtime safety 2026-08-11 15:13:13 +08:00
Haoran
b36dbcd84f Consolidate agent harness course into 19 lessons 2026-08-04 02:25:40 +08:00
Haoran
2affb3f345 docs: simplify Chinese course prose 2026-07-31 03:54:12 +08:00
Haoran
4a14529774 docs: rename s19 to integrated harness 2026-07-31 03:35:17 +08:00
Haoran
2d69019342 feat: consolidate course into 21 lessons 2026-07-31 03:15:58 +08:00
Haoran
4bc33ec858 docs: make workflow and goal lessons harness-first 2026-07-30 20:05:33 +08:00
Haoran
cb8fae1bdd feat: refresh course through workflow and goal loops 2026-07-30 19:14:04 +08:00
gui-yue
99a1e52b36 fix: harden compaction pair handling 2026-06-07 12:35:08 +08:00
wanna
7891c25c12 fix: keep tool-use/result pairs intact during compaction
Preserve assistant tool_use / user tool_result adjacency when compaction trims message history.

Fixes #325.

Squashed original PR commits:

- Fix compaction breaking tool-use/result pairs

- Simplify compaction boundary fix
2026-06-07 12:35:00 +08:00
gui-yue
abe09a9ccb Sync generated course content 2026-05-31 17:27:29 +08:00
Haoran
fdd7d2a851 feat: complete web curriculum visuals 2026-05-25 22:38:02 +08:00
copilot-swe-agent[bot]
13409478ef Optimize Chinese translations: preserve English proper nouns (Skills, Agent, Subagent, Context Compact, etc.)
Co-authored-by: wbxl2000 <57169560+wbxl2000@users.noreply.github.com>
2026-03-16 14:23:59 +00:00
CrazyBoyM
dbffe7c8d0 fix: address community issues #37 #30 #36
- s03: inject reminder into tool_result instead of mutating history (#37)
- s05: SkillLoader uses rglob("SKILL.md") + frontmatter name priority,
  matching Agent Skills standard (#30, PR #34)
- CI: upgrade actions/checkout and actions/setup-node to v6 (#36)
- docs: update s05 skill directory structure in all 3 languages
2026-02-28 00:09:57 +08:00
CrazyBoyM
4f39ee4512 fix session doc 2026-02-27 02:19:54 +08:00
CrazyBoyM
665831c774 better doc 2026-02-27 01:11:57 +08:00
CrazyBoyM
aea8844bac add worktree & up task、teammate etc 2026-02-24 01:44:44 +08:00
CrazyBoyM
c6a27ef1d7 feat: build an AI agent from 0 to 1 -- 11 progressive sessions
- 11 sessions from basic agent loop to autonomous teams
- Python MVP implementations for each session
- Mental-model-first docs in en/zh/ja
- Interactive web platform with step-through visualizations
- Incremental architecture: each session adds one mechanism
2026-02-21 17:02:43 +08:00