Haoran
cce031e632
fix: harden subprocess output decoding across lessons
2026-08-26 01:05:16 +08:00
Haoran
922265145b
fix: complete readline prompt coverage
2026-08-25 21:56:24 +08:00
Haoran
b99447946d
Merge remote-tracking branch 'shareai/main' into fix/pr-536-readline-prompt-wrap
...
# Conflicts:
# web/src/data/generated/versions.json
2026-08-25 21:38:38 +08:00
Haoran
199402f9d4
fix: use UTF-8 for text file operations
2026-08-24 20:28:37 +08:00
Haoran
6d70d2e071
fix: preserve tool results during context compaction
2026-08-23 11:50:52 +08:00
Haoran
61c3e64595
fix: support bounded recursive glob across lessons
2026-08-23 11:28:14 +08:00
Jared
1342a990a2
fix(s08): support recursive glob and conditional micro compact
2026-08-20 16:39:45 +08:00
Unilinear
fe32cd7ecf
fix: preserve wrapped input display in colored prompts
2026-08-20 14:44:01 +08:00
Haoran
b6b5f331ab
fix: preserve only unseen tool results
2026-08-16 17:32:53 +08:00
123456wda
b5bd0ddfa1
fix: preserve latest tool result batch during compaction
2026-08-15 21:14:22 +08:00
Haoran
168fff86dd
Fix empty tool-use response handling
2026-08-15 00:03:45 +08:00
Haoran
7e2f2fd99b
refactor: streamline the course to 17 lessons
2026-08-12 03:02:42 +08:00
Haoran
b36dbcd84f
Consolidate agent harness course into 19 lessons
2026-08-04 02:25:40 +08:00
Haoran
13dc5396bb
feat: refresh context compaction lesson
2026-07-31 15:52:53 +08:00
Haoran
2affb3f345
docs: simplify Chinese course prose
2026-07-31 03:54:12 +08:00
Haoran
2d69019342
feat: consolidate course into 21 lessons
2026-07-31 03:15:58 +08:00
Haoran
cb8fae1bdd
feat: refresh course through workflow and goal loops
2026-07-30 19:14:04 +08:00
root
b6eb5c0f3b
docs(s08): clarify reactive_compact aggressive wording refers to trigger, not compression
...
The original phrasing "more aggressive than compact_history" was
ambiguous: the code shows reactive_compact is actually more
conservative in compression (keeps ~5 recent messages vs replacing
everything with a summary). The real difference is the trigger
mechanism — reactive_compact is an emergency response to a 413
error, not a proactive threshold-based trigger.
Clarify in all three README languages that the aggressiveness is
about the trigger, not the compression strategy.
Closes #467
2026-07-28 22:17:25 +08:00
gui-yue
ef3e88eead
Merge pull request #364 from costajohnt/refactor/reactive-compact-summarize-old-history
...
refactor: summarize only trimmed history in reactive_compact
2026-06-22 15:54:24 +08:00
costajohnt
90a044883f
docs: align snip_compact README guards with code
...
Match the snip_compact teaching snippet (en/zh/ja) to code.py: add the
`head_end > 0` head guard and the `tail_start > 0 and tail_start <
len(messages)` tail bounds check before indexing messages, mirroring the
reactive_compact alignment.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_011UJumwVeBXSGYh8nSzoVTF
2026-06-21 16:52:41 -07:00
costajohnt
7659f28976
docs: align reactive_compact README guard with code
...
The reactive_compact README snippets (en/zh/ja) used a shortened tail
boundary check, while code.py guards with `tail_start > 0 and tail_start
< len(messages)` before reading messages[tail_start]. Match the snippets
to the actual code so the teaching example stays consistent.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_011UJumwVeBXSGYh8nSzoVTF
2026-06-21 16:47:09 -07:00
gui-yue
58ded12b98
Merge pull request #336 from clysir/fix-s09-subagent-arg
...
Fix s09 subagent tool argument mismatch
2026-06-21 22:55:32 +08:00
gui-yue
8daed25878
Fix s08 subagent tool argument mismatch
2026-06-21 22:32:41 +08:00
John Costa
49b3822247
refactor: summarize only trimmed history in reactive_compact
...
reactive_compact summarized the full message history before slicing off
the recent tail, so the kept tail was summarized and then re-attached
verbatim, and the emergency prompt-too-long path re-summarized the whole
oversized context. Move the summarize_history call below the tail
computation (including the tool_use/tool_result pair adjustment) and
summarize only messages[:tail_start], so the summary covers older history
while the recent tail stays verbatim.
Applied to the duplicated function in s08, s09, and s20, with the s08
README snippets (en/zh/ja) updated to match. Adds tests covering the
normal path and the case where a tool pair straddles the tail boundary.
Fixes #350
2026-06-15 21:55:21 -07:00
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
ec9ea874e6
Merge pull request #342 from Bill-Billion/codex/fix-todo-write-string-input
...
fix: handle todo_write string inputs
2026-06-03 23:33:36 +08:00
Haoran
ee9a747e09
fix: handle todo_write string inputs for issue 340
...
Co-authored-by: gui-yue <yuemeng.gui@gmail.com >
2026-06-03 23:24:34 +08:00
gui-yue
ae94cda0ed
Document read_file compact trade-off
2026-06-03 22:40:37 +08:00
Haoran
4d12ca93de
fix: prevent course svg text overflow
2026-05-26 11:17:58 +08:00
Gui-Yue
6d48bc978b
fix: align TodoWrite memory model with task system docs
2026-05-21 23:55:00 +08:00
gui-yue
1baf1aca5a
Follow up PR #265 : refine chapters, diagrams, and add S20 ( #283 )
...
* feat: s01-s14 docs quality overhaul — tool pipeline, single-agent, knowledge & resilience
Rewrite code.py and README (zh/en/ja) for s01-s14, each chapter building
incrementally on the previous. Key fixes across chapters:
- s01-s04: agent loop, tool dispatch, permission pipeline, hooks
- s05-s08: todo write, subagent, skill loading, context compact
- s09-s11: memory system, system prompt assembly, error recovery
- s12-s14: task graph, background tasks, cron scheduler
All chapters CC source-verified. Code inherits fixes forward (PROMPT_SECTIONS,
json.dumps cache, real-state context, can_start dep protection, etc.).
* feat: s15-s19 docs quality overhaul — multi-agent platform: teams, protocols, autonomy, worktree, MCP tools
Rewrite code.py and README (zh/en/ja) for s15-s19, the multi-agent platform
chapters. Each chapter inherits all previous fixes and adds one mechanism:
- s15: agent teams (TeamCreate, teammate threads, shared task list)
- s16: team protocols (plan approval, shutdown handshake, consume_inbox)
- s17: autonomous agents (idle polling, auto-claim, consume_lead_inbox)
- s18: worktree isolation (git worktree, bind_task, cwd switching, safety)
- s19: MCP tools (MCPClient, normalize_mcp_name, assemble_tool_pool, no cache)
All appendix source code references verified against CC source. Config priority
corrected: claude.ai < plugin < user < project < local.
* fix: 5 regressions across s05-s19 — glob safety, todo validation, memory extraction, protocol types, dep crash
- s05-s09: glob results now filter with is_relative_to(WORKDIR) (inherited from s02)
- s06-s08: todo_write validates content/status required fields (inherited from s05)
- s09: extract_memories uses pre-compression snapshot instead of compacted messages
- s16: submit_plan docstring clarifies protocol-only (not code-level gate)
- s17-s19: match_response restores type mismatch validation (from s16)
- s17-s19: claim_task deps list handles missing dep files without crashing
* fix: s12 Todo V2 logic reversal, s14/s15 cron range validation, s18/s19 worktree name validation
- s12 README (zh/en/ja): fix Todo V2 direction — interactive defaults to Task,
non-interactive/SDK defaults to TodoWrite. Fix env var name to
CLAUDE_CODE_ENABLE_TASKS (not TODO_V2).
- s14/s15: add _validate_cron_field with per-field range checks (minute 0-59,
hour 0-23, dom 1-31, month 1-12, dow 0-6), step > 0, range lo <= hi.
Replace old try/except validation that only caught exceptions.
- s18/s19: add validate_worktree_name() to remove_worktree and keep_worktree,
not just create_worktree.
* fix: align s16-s19 teaching tool consistency
* fix pr265 chapter diagrams
* Add comprehensive s20 harness chapter
* Fix chapter smoke test regressions
* Clarify README tutorial track transition
---------
Co-authored-by: Haoran <bill-billion@outlook.com >
2026-05-20 21:45:38 +08:00
