Artur Mukhamadiev a647406729 backend: per-query call budgets configurable from the environment ...

The 100 Confluence / 50 model call caps per query were fixed Settings
defaults. CONFLUENCE_WEB_MAX_CONFLUENCE_CALLS and CONFLUENCE_WEB_MAX_MODEL_CALLS
now set them (1-1000 each, validated at startup). Cache hits stay free. The
request history still keeps at most 100 tool entries, so a Confluence budget
above 100 drops later entries with the existing history_overflow warning;
documented next to the setting.

2026-09-15 14:29:37 +03:00

..

conftest.py

backend: FastAPI backend track handoff (contract revision 1)

2026-09-14 21:57:54 +03:00

test_admission.py

backend: admission queue with reservations

2026-09-15 13:38:59 +03:00

test_app.py

backend: FastAPI backend track handoff (contract revision 1)

2026-09-14 21:57:54 +03:00

test_artifacts.py

backend: FastAPI backend track handoff (contract revision 1)

2026-09-14 21:57:54 +03:00

test_confluence.py

backend: FastAPI backend track handoff (contract revision 1)

2026-09-14 21:57:54 +03:00

test_docker_live.py

integration: align backend container launch and serve frontend at root

2026-09-14 22:01:01 +03:00

test_history.py

backend: FastAPI backend track handoff (contract revision 1)

2026-09-14 21:57:54 +03:00

test_model.py

backend: FastAPI backend track handoff (contract revision 1)

2026-09-14 21:57:54 +03:00

test_queue_api.py

backend: admission queue with reservations

2026-09-15 13:38:59 +03:00

test_review_regressions.py

docs: drop handoff, review and report references

2026-09-15 00:23:43 +03:00

test_runner.py

backend: FastAPI backend track handoff (contract revision 1)

2026-09-14 21:57:54 +03:00

test_settings.py

backend: per-query call budgets configurable from the environment

2026-09-15 14:29:37 +03:00

test_transport.py

backend: FastAPI backend track handoff (contract revision 1)

2026-09-14 21:57:54 +03:00