cflmy and Cursor
e3e2cfa9d1
fix(agent): writeback param shadow + Wave B1 dump/harness
...
step/plan writeback=True shadowed lib/writeback; persist via host_writeback_record. Align ZH context builder, add dump_step_context, lock offline harness.
Co-authored-by: Cursor <cursoragent@cursor.com >
2026-09-04 11:24:50 +08:00
cflmy and Cursor
d1b4e62d4d
feat(agent): Wave B0 constitution demos + harness
...
Lock code-as-doc / call_site / OKF as first-class: reorder step
context, ship agent-pong and okf-flywheel examples, offline harness,
and skill/docs refresh. Dev LLM template via .env.example only.
Co-authored-by: Cursor <cursoragent@cursor.com >
2026-09-04 11:17:25 +08:00
cflmy and Cursor
4c37e79dae
docs(agent): record post-A4 framework gaps and next-wave B0–B5
...
Capture productization, eval, live MCP, resume/HITL, and metrics gaps after the A0–A4 optimize loop; link from roadmap and doc index.
Co-authored-by: Cursor <cursoragent@cursor.com >
2026-08-28 17:56:31 +08:00
cflmy and Cursor
9a8545b725
feat(agent): A4 corpus search and MCP fixture evidence tools
...
Add local keyword corpus_search and offline MCP fixture adapters as parent CALL tools; keep authority on workbook .mq.md.
Co-authored-by: Cursor <cursoragent@cursor.com >
2026-08-28 17:47:59 +08:00
cflmy and Cursor
ee3116513b
feat(agent): A3 context budget and progressive READ disclose
...
Budget source/skill in step prompts with truncation markers; allow READ:source|skill deepen; parent READ:skill.
Co-authored-by: Cursor <cursoragent@cursor.com >
2026-08-28 17:26:16 +08:00
cflmy and Cursor
729357b7c0
feat(agent): A2 process visibility — events always on plan result
...
Record decision/round/done without requiring stream; render process timeline on view plan cards; keep SSE gated on stream=True.
Co-authored-by: Cursor <cursoragent@cursor.com >
2026-08-28 17:06:59 +08:00
cflmy and Cursor
07ab7d52c6
feat(agent): A1 OKF reuse flywheel — list_tasks curation and plan match
...
Enrich list_tasks for soft_match curation; expose match/score on plan hits; add offline plan-hit gold.
Co-authored-by: Cursor <cursoragent@cursor.com >
2026-08-28 16:53:27 +08:00
cflmy and Cursor
d7be903297
test(agent): A0 gold for multi-CONTINUE patches and solidify
...
Offline coverage: two precise workbook patches then agent_workbook_solidify
freezes the step worker into a quoted return.
Co-authored-by: Cursor <cursoragent@cursor.com >
2026-08-28 16:41:44 +08:00
cflmy and Cursor
d0b184939f
fix(agent): harden workbook patches against whole-file rewrites
...
Reject large whole-file FIND spans, narrow soft=True to miss-only, check
decompose CONTINUE patch counts, and unit-test workbook_solidify.
Co-authored-by: Cursor <cursoragent@cursor.com >
2026-08-28 16:22:39 +08:00
cflmy and Cursor
c36383bf28
docs(agent): research frameworks vs Marqdo document-driven advantages
...
Add detailed survey of LangGraph/CrewAI/SDK landscape, lock Marqdo
differentiators, and sketch A0–A4 optimize roadmap for ext/agent.
Co-authored-by: Cursor <cursoragent@cursor.com >
2026-08-28 16:06:11 +08:00