Wistom Zhang 1fbc06279a

feat(benchmark): add offline memory vs project-context comparison suite (part of #7884) (#8058) ...

* feat(benchmark): add offline memory vs project-context comparison suite (part of #7884)

* fix(benchmark): route prompts through DynamicContextMiddleware, flatten rows, and share test run

* refactor(benchmark): run through local Gateway and simplify first-pass suite (#7884)

* docs(agents): keep context memory benchmark guidance within chain budget

* fix(benchmark): verify DeerMem scope rejection

---------

Co-authored-by: Totoro <msy626836554@gmail.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>

2026-11-10 14:45:56 +08:00

..

benchmark

feat(benchmark): add offline memory vs project-context comparison suite (part of #7884) (#8058)

2026-11-10 14:45:56 +08:00

_autogen_revision.py

feat(persistence): wire alembic migrations, bootstrap schema on startup (#3706)

2026-06-24 13:57:12 +08:00

build_fixture_from_jsonl.py

fix(replay-e2e): key fixtures by caller and conversation (#3453)

2026-06-09 21:58:31 +08:00

e2e_safety_termination_demo.py

fix(runtime): suppress tool execution when provider safety-terminates with tool_calls (#3035)

2026-05-22 21:20:28 +08:00

eval_memory_prescreen.py

refactor(agent): ground runtime decisions in structured evidence (#7986)

2026-11-08 22:00:23 +08:00

eval_typesafe_risk_gate.py

feat(typesafe): make the risk-gate eval rubric-calibratable and its policy reproducible (#6179)

2026-10-02 22:56:24 +08:00

manual_task_continuity_check.py

feat: add opt-in task notes and compacted history recall (#5382)

2026-09-12 21:01:46 +08:00

migrate_agents_to_db.py

docs: run configuration and migration commands in the backend environment (#6425)

2026-10-07 19:06:59 +08:00

migrate_memory_markdown.py

feat(memory): add incremental agent-scoped Markdown fact storage (#4279)

2026-07-22 07:46:03 +08:00

migrate_user_isolation.py

fix(migration): read thread owners from the configured database (#6450)

2026-10-08 10:27:10 +08:00

record_gateway.py

fix(replay-e2e): key fixtures by caller and conversation (#3453)

2026-06-09 21:58:31 +08:00

run_producer_fencing.py

fix(runtime): persistently fence stale run event producers (#7619)

2026-11-02 15:26:42 +08:00

run_replay_gateway.py

test(e2e): deterministic record/replay front-back contract verification (#3365)

2026-06-08 12:35:03 +08:00

typesafe_risk_gate_cases.json

feat(guardrails): add TypeSafe (Jev) pre-execution tool risk gate (#5712)

2026-09-24 18:20:31 +08:00