souvikk.kundu 3ae085c639 feat(router_strategy): add hybrid router combining complexity gating with per-tier MAB selection ... Two-layer routing strategy: Layer 1 classifies request complexity into SIMPLE/MEDIUM/COMPLEX/REASONING tiers using heuristic scoring, Layer 2 picks the best model within each tier using a per-tier multi-armed bandit (Thompson Sampling, UCB, or Epsilon-Greedy). Per-tier bandits learn independently, so a model that is fast for simple queries but slow for complex ones gets scored separately at each tier. Includes eval script and 50 unit tests covering all three bandit algorithms, classification, reward recording, convergence, and tier priors.		2026-09-02 20:17:04 -07:00
..
adaptive_router_demo	feat: commit new adaptive routing	2026-04-18 21:29:39 -07:00
health_check	feat(rate-limiter): allow opting out of v3 TPM reservation and Redis circuit breaker (#30211)	2026-06-11 10:34:26 -07:00
benchmark_anthropic_messages_perf.py	perf: reduce per-request and per-chunk overhead across Anthropic streaming hot paths (#28289)	2026-05-23 12:15:59 -07:00
benchmark_chat_completions_perf.py	perf: eliminate per-request callback scanning on proxy hot path (#27858)	2026-05-14 09:28:31 -07:00
benchmark_mock.py	style: run black formatter on files from main merge	2026-04-17 13:02:59 -07:00
benchmark_model_response_creator.py	fix: improve bedrock streaming hot path perf (#28720)	2026-05-28 11:31:37 -07:00
benchmark_proxy_vs_provider.py	style: run black formatter on files from main merge	2026-04-17 13:02:59 -07:00
benchmark_streaming_chunk_overhead.py	feat: litellm oss 110626 (#30202)	2026-06-11 22:30:26 -07:00
budget_ratchet_check.py	fix(lint): let the ratchet guard recognise a graduated rule	2026-08-07 23:11:23 -07:00
check_type_discipline.py	fix(scripts): unwrap PEP 604 unions in LIT002 TypedDict detection	2026-08-13 20:01:35 -07:00
create_litellm_branch.ps1	feat: add script to create branches with litellm_ prefix (#17606)	2025-12-06 10:41:39 -08:00
create_litellm_branch.sh	enhance: create_litellm_branch tool to be more robust (#17874)	2025-12-12 05:35:50 -08:00
create_team_key_and_submit_guardrail.sh	feat(guardrails): team-based guardrail registration and approval workflow (#22459)	2026-03-02 22:06:49 -08:00
efficiency_eval_prompts.py	feat(router_strategy): add hybrid router combining complexity gating with per-tier MAB selection	2026-09-02 20:17:04 -07:00
eval_compression.py	Prompt Compression - add it to the proxy (#25729)	2026-04-20 15:08:00 -07:00
gate_slot_lock.py	refactor(make): stop queueing bootstrap for a machine-wide gate slot	2026-08-15 21:53:28 +00:00
install-cli.sh	fix(install): pass an explicit Python version request to uv tool install	2026-07-26 21:02:35 -07:00
install.sh	fix(install): pass an explicit Python version request to uv tool install	2026-07-26 21:02:35 -07:00
install_git_hooks.sh	build(lint): rename make pre-commit to make check with a working-tree fallback	2026-08-08 03:25:35 -07:00
mock_bedrock_passthrough_target.py	Refactor Bedrock response stream shape handling (#27257)	2026-05-06 17:39:38 -07:00
mock_grayswan_timeout_server.py	implement failopen option default to True on grayswan guardrail (#18266)	2026-01-06 15:17:05 +05:30
mutation_report.py	ci: add manually-triggered mutation testing workflow (#27576)	2026-05-11 15:19:57 -07:00
pre_commit_lint.sh	feat(scripts): queue heavy gates behind a machine-wide slot lock	2026-08-14 17:22:32 -07:00
prisma_generate_if_needed.py	fix(lint): generate the prisma client into the gate-owned venv	2026-08-06 01:54:26 -07:00
ruff_strict_gate.py	feat(scripts): queue heavy gates behind a machine-wide slot lock	2026-08-14 17:22:32 -07:00
test_agent_mcp_endpoints.sh	Agents - assign tools (#22064)	2026-02-25 11:44:30 -08:00
test_custom_router_hybrid_v1.py	feat(router_strategy): add hybrid router combining complexity gating with per-tier MAB selection	2026-09-02 20:17:04 -07:00
test_guardrails_register_endpoints.sh	feat(guardrails): team-based guardrail registration and approval workflow (#22459)	2026-03-02 22:06:49 -08:00
test_tool_allowlist_script.py	style: run black formatter on files from main merge	2026-04-17 13:02:59 -07:00
tpm_headline_test.sh	fix: atomic TPM rate limit (#27001)	2026-05-05 16:58:07 -07:00
type_check_gate.py	feat(scripts): queue heavy gates behind a machine-wide slot lock	2026-08-14 17:22:32 -07:00
type_discipline_gate.py	feat(scripts): queue heavy gates behind a machine-wide slot lock	2026-08-14 17:22:32 -07:00
verify_adaptive_router.py	feat: add adaptive routing to litellm	2026-04-18 16:35:17 -07:00
with_dashboard_node.sh	fix(bootstrap): fail fast when nvm cannot activate the pinned node	2026-08-04 21:18:58 -07:00