a09d4afacd
fix: pipeline排序/runDic映射/label-master repeatable/达标优先级
...
- pipeline items 按 first_ts 自然时间排序，去掉 hardcoded section_order
- augment step-detail 去掉 R{n-1} 偏移，直接用本轮 runDic（与 resolve_run_ids.sh 实际行为对齐）
- 加 BundledSkill.repeatable 字段，label-master 标记 repeatable:true 跳过 duplicate detection
- SKILL.md/program.md: 目标集≥95%最高优先级，未达标前其他集合轻微下降不回滚
- SKILL.md/program.md: 禁止正则脚本替代 label-master 语义复核
- program.md: 每轮 SFT 前必须展示训练数据组成
- resolve_run_ids.sh: 修正注释（SFT_RUNDIC = 当轮 eval workflow id）
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com >
2026-05-26 14:10:32 +08:00
f068311cac
backend/frontend/runtime: 训练面板 / session 隔离 / agent runtime 调整
...
- backend/api/server.py：训练 step-detail / pipeline 卡片排序逻辑
- frontend：thread-list / thread / training-pipeline-panel / step-detail-sheet 配套调整，新增 metrics-chart-panel
- src/agent_*：tool spec / runtime / prompting 配套
- .gitignore 加 .logs/
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com >
2026-05-25 11:43:10 +08:00
0eb57f3f42
Isolate plan and task runtime per session
2026-05-13 20:07:09 +08:00
9984d35d1f
Prefer python exec for complex file writes
2026-05-13 16:35:17 +08:00
8a93319f1b
Fix ask-user review pause in web runs
2026-05-13 11:11:40 +08:00
126f35ae46
Improve file writing and activity replay
2026-05-12 20:48:25 +08:00
64787498dd
Improve write_file fallback handling
2026-05-12 19:52:41 +08:00
413a37b32c
Stream model events to activity panel
2026-05-11 21:24:32 +08:00
4c29ce21f1
Make product-data generation resumable
2026-05-11 20:13:08 +08:00
41eb36a704
Avoid draft files in product-data generation
2026-05-11 19:56:29 +08:00
0e2a00990f
Stabilize product data export flow
2026-05-11 11:46:09 +08:00
9e94648ae6
Stop repeated duplicate skill loops
2026-05-08 10:40:01 +08:00
de6bb12ae5
Guard skill and continuation loops
2026-05-07 20:26:59 +08:00
d57570e527
Persist active run event history
2026-05-07 17:40:46 +08:00
9d7d496443
Add session scoped runs and cancellation
2026-05-07 16:26:20 +08:00
1aafc0fce7
Improve data skill routing and tool organization
2026-05-06 21:46:09 +08:00
9ca675be0d
Improve WebUI streaming and Python tooling
2026-05-06 20:37:17 +08:00
7d4ae3e7ba
Add assistant-ui data agent frontend
2026-05-06 16:18:32 +08:00
97bf5b9a54
Show data agent review summaries in sessions
2026-04-30 15:11:46 +08:00
c1951d6e4d
Pause data generation for human review
2026-04-29 19:31:29 +08:00
a040d80096
Add directory-based project skills
2026-04-28 10:17:23 +08:00
cfd3bb9ca7
Implemented the next missing parity slice around clearing session env vars on /clear.
...
Wires clear_session_env_vars() into LocalCodingAgent.clear_runtime_state so the
/clear slash command now drops session-scoped env vars alongside the rest of the
ephemeral runtime state, matching commands/clear/caches.ts:127.
2026-04-20 00:52:28 +02:00
872f4f89b5
Implemented the next missing parity slice around agent configurations.
2026-04-17 05:15:17 +02:00
02674ba594
Implemented the next missing parity slice around agent configurations.
2026-04-17 05:03:19 +02:00
17e0da9b5b
update agnt
2026-04-15 03:31:08 +02:00
a4aaf814d7
Here's a summary of all the features I ported from the TypeScript source to Python:
2026-04-15 02:29:22 +02:00
b5e5824a56
Implemented the next parity slice: prompt-budget preflight and context collapse.
...
Core changes:
- Added claw-code/src/token_budget.py for projected prompt size, chat-framing overhead, output reserve, and soft/hard input limits.
- Wired preflight prompt-length validation and auto-compact/context collapse into claw-code/src/agent_runtime.py.
- Extended claw-code/src/compact.py so compaction reports usage back to the runtime.
- Added inspection surfaces in claw-code/src/agent_slash_commands.py and claw-code/src/main.py:
- /token-budget and /budget
- token-budget
- Hardened claw-code/src/tokenizer_runtime.py so arbitrary simple model names fall back cleanly instead of trying a slow Transformers
lookup.
- Exported the new helpers in claw-code/src/__init__.py.
Docs and tracking:
- Updated claw-code/PARITY_CHECKLIST.md to mark prompt-length validation, token-budget calculation, and auto-compact/context collapse as
done.
- Updated claw-code/README.md and claw-code/TESTING_GUIDE.md with the new commands and behavior.
Tests:
- Added claw-code/tests/test_token_budget.py.
- Updated claw-code/tests/test_agent_runtime.py, claw-code/tests/test_agent_slash_commands.py, claw-code/tests/test_main.py, and claw-code/
tests/test_agent_context_usage.py.
- Verified with:
- /data/fs201059/aa17626/miniconda3/bin/python3 -m compileall src tests
- /data/fs201059/aa17626/miniconda3/bin/python3 -m unittest -v tests.test_token_budget
tests.test_agent_runtime.AgentRuntimeTests.test_agent_rejects_prompt_before_backend_when_preflight_input_budget_is_exceeded
tests.test_agent_runtime.AgentRuntimeTests.test_agent_auto_compacts_context_before_next_model_call tests.test_agent_slash_commands
tests.test_main tests.test_compact tests.test_tokenizer_runtime tests.test_agent_context_usage
- Result: 71 tests, OK
2026-04-11 01:38:19 +02:00
aacf0a212a
Created src/prompt_constants.py (550+ lines) porting all constants from npm src/constants/:
...
┌──────────────────┬───────────────────────────┬───────────────────────────────────────────────┐
│ Category │ npm Source │ Items │
├──────────────────┼───────────────────────────┼───────────────────────────────────────────────┤
│ Product metadata │ product.ts │ URLs, base URLs │
├──────────────────┼───────────────────────────┼───────────────────────────────────────────────┤
│ System prefixes │ system.ts │ 3 prompt prefixes │
├──────────────────┼───────────────────────────┼───────────────────────────────────────────────┤
│ Cyber risk │ cyberRiskInstruction.ts │ Safety instruction │
├──────────────────┼───────────────────────────┼───────────────────────────────────────────────┤
│ API limits │ apiLimits.ts │ 10 image/PDF/media limits │
├──────────────────┼───────────────────────────┼───────────────────────────────────────────────┤
│ Tool limits │ toolLimits.ts │ 6 result size constants │
├──────────────────┼───────────────────────────┼───────────────────────────────────────────────┤
│ Spinner verbs │ spinnerVerbs.ts │ 187 whimsical gerunds │
├──────────────────┼───────────────────────────┼───────────────────────────────────────────────┤
│ Completion verbs │ turnCompletionVerbs.ts │ 8 past-tense verbs │
├──────────────────┼───────────────────────────┼───────────────────────────────────────────────┤
│ Figures/symbols │ figures.ts │ 25 Unicode UI symbols │
├──────────────────┼───────────────────────────┼───────────────────────────────────────────────┤
│ XML tags │ xml.ts │ 30+ tag constants │
├──────────────────┼───────────────────────────┼───────────────────────────────────────────────┤
│ Messages │ messages.ts │ NO_CONTENT_MESSAGE │
├──────────────────┼───────────────────────────┼───────────────────────────────────────────────┤
│ Date utilities │ common.ts │ 4 functions │
├──────────────────┼───────────────────────────┼───────────────────────────────────────────────┤
│ Section caching │ systemPromptSections.ts │ Memoized/volatile sections │
├──────────────────┼───────────────────────────┼───────────────────────────────────────────────┤
│ Output styles │ outputStyles.ts │ 3 built-in configs │
├──────────────────┼───────────────────────────┼───────────────────────────────────────────────┤
│ Prompt helpers │ prompts.ts │ Knowledge cutoff, language, scratchpad, hooks │
└──────────────────┴───────────────────────────┴───────────────────────────────────────────────┘
91 new tests in tests/test_prompt_constants.py. All 17 SQL todos done.
2026-04-08 00:02:53 +02:00
c17c2768eb
Implemented the next parity slice.
...
New runtime/code:
- src/ask_user_runtime.py
- src/team_runtime.py
New real tools in src/agent_tools.py:
- ask_user_question
- team_create
- team_delete
- team_list
- team_get
- send_message
- team_messages
- notebook_edit
2026-04-07 03:48:20 +02:00
a5629295ac
Implemented the next parity slice.
...
New runtime/code:
- src/ask_user_runtime.py
- src/team_runtime.py
New real tools in src/agent_tools.py:
- ask_user_question
- team_create
- team_delete
- team_list
- team_get
- send_message
- team_messages
- notebook_edit
2026-04-07 02:51:30 +02:00
783145fe6a
add mcp and online search
2026-04-05 02:35:49 +02:00
3f31cee395
add claw-code-agent/src/plan_runtime.py and claw-code-agent/src/background_runtime.py. The agent now has a real
...
persistent plan runtime with update_plan, plan_get, and plan_clear, plus plan-to-task sync wired through claw-code-agent/src/
agent_tools.py, claw-code-agent/src/agent_runtime.py, claw-code-agent/src/agent_context.py, claw-code-agent/src/agent_prompting.py, and claw-code-agent/src/
agent_slash_commands.py. New local plan slash commands are /plan and /planner.
2026-04-03 18:31:25 +02:00
4de3da10e4
add test guide cases
2026-04-03 16:50:19 +02:00
5ad10c660c
add File-history snapshot ids and replay summaries for file edits
2026-04-02 22:19:32 +02:00
9d90d6a10a
add ىثص ؤخقث شلثىف قعىفهةث
2026-04-02 22:08:24 +02:00
2c6763eb08
add new agent components
2026-04-02 21:12:48 +02:00
27aff5611b
first commit
2026-04-01 21:51:49 +02:00
wangsenhao