scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/40036/head at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:47 +00:00
fc74942ed8 Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_lit_4966_user_mcp_inherited_servers
192e38fa7b feat(skills): semantic search over the LiteLLM-hosted skill registry (#39401)
c949843157 fix(ui): send empty vector_stores when the last team vector store is removed (#40144)
cc287a7d8f fix(ui): hide the Create Vector Store flow from non proxy admins (#40148)
eea4c860f7 feat(ui): add key-scoped auto-router usage tab (#39999)
Compare 109 commits »
scriptoriumadmin synced commits to refs/pull/40035/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:47 +00:00
9b74e6f34e Merge pull request #40009 from BerriAI/litellm_lit_7039_least_busy_shared_counts
f769aa4675 fix(router): give cooldowns their own cache so siblings see a bench in ~1s (#40025)
eeef03f122 chore: merge litellm_internal_staging into litellm_lit_7039_least_busy_shared_counts
a85c3152ca fix(proxy): load db credentials in the model reconcile so a worker never serves a model before its credential (#39876)
Compare 232 commits »
scriptoriumadmin synced commits to refs/pull/40049/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:47 +00:00
9b74e6f34e Merge pull request #40009 from BerriAI/litellm_lit_7039_least_busy_shared_counts
f769aa4675 fix(router): give cooldowns their own cache so siblings see a bench in ~1s (#40025)
eeef03f122 chore: merge litellm_internal_staging into litellm_lit_7039_least_busy_shared_counts
a85c3152ca fix(proxy): load db credentials in the model reconcile so a worker never serves a model before its credential (#39876)
Compare 232 commits »
scriptoriumadmin synced commits to refs/pull/40048/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:47 +00:00
1a791b7d2b Merge a78aa1fdaacebe5fe22d128ecf22c5be45b62e6a into 9b74e6f34e
9b74e6f34e Merge pull request #40009 from BerriAI/litellm_lit_7039_least_busy_shared_counts
f769aa4675 fix(router): give cooldowns their own cache so siblings see a bench in ~1s (#40025)
eeef03f122 chore: merge litellm_internal_staging into litellm_lit_7039_least_busy_shared_counts
a85c3152ca fix(proxy): load db credentials in the model reconcile so a worker never serves a model before its credential (#39876)
Compare 232 commits »
scriptoriumadmin synced commits to refs/pull/40029/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:46 +00:00
728d0953af ci: simplify Rust checks and remove wheel PR comments (#39975)
Compare 2 commits »
scriptoriumadmin synced commits to refs/pull/40033/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:46 +00:00
728d0953af ci: simplify Rust checks and remove wheel PR comments (#39975)
168a0055a2 chore(lint): stop ratcheting *-budget.json on PR branches (#39937)
Compare 3 commits »
scriptoriumadmin synced commits to refs/pull/40034/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:46 +00:00
9b74e6f34e Merge pull request #40009 from BerriAI/litellm_lit_7039_least_busy_shared_counts
f769aa4675 fix(router): give cooldowns their own cache so siblings see a bench in ~1s (#40025)
eeef03f122 chore: merge litellm_internal_staging into litellm_lit_7039_least_busy_shared_counts
a85c3152ca fix(proxy): load db credentials in the model reconcile so a worker never serves a model before its credential (#39876)
Compare 232 commits »
scriptoriumadmin synced commits to refs/pull/40018/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:46 +00:00
c899912f49 Merge pull request #40287 from BerriAI/litellm_/release-version-bump-787548
0175c7da1c feat(router): resolve max_tokens to the tier model's ceiling on auto-routed requests (#40209)
9e18526887 feat(deploy): metrics sidecar and separate metrics port in Helm and Terraform (#40163)
4a3a78c256 feat(complexity_router): rebalance heuristic weights in the dashboard and grade custom dimensions by match count (#40205)
Compare 254 commits »
scriptoriumadmin synced commits to refs/pull/40024/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:46 +00:00
9b74e6f34e Merge pull request #40009 from BerriAI/litellm_lit_7039_least_busy_shared_counts
f769aa4675 fix(router): give cooldowns their own cache so siblings see a bench in ~1s (#40025)
eeef03f122 chore: merge litellm_internal_staging into litellm_lit_7039_least_busy_shared_counts
a85c3152ca fix(proxy): load db credentials in the model reconcile so a worker never serves a model before its credential (#39876)
Compare 234 commits »
scriptoriumadmin synced commits to refs/pull/40018/head at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:46 +00:00
82c626e25d test(cost): trim the docstrings on the realtime cost-map regressions
9058a84192 fix(cost): correct gemini-live-2.5-flash-native-audio limits and capabilities
4db0efe3c7 fix(pricing): correct cached-token fields on realtime cost-map entries
168a0055a2 chore(lint): stop ratcheting *-budget.json on PR branches (#39937)
02522a5441 Merge pull request #39983 from BerriAI/litellm_lit_7081_azure_ai_gpt_6_astra_pricing
Compare 401 commits »
scriptoriumadmin synced commits to refs/pull/40016/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:46 +00:00
b9bf335ecd Merge 65926aabf7e7bf749a1671938893e3c0074509b1 into 9b74e6f34e
9b74e6f34e Merge pull request #40009 from BerriAI/litellm_lit_7039_least_busy_shared_counts
f769aa4675 fix(router): give cooldowns their own cache so siblings see a bench in ~1s (#40025)
eeef03f122 chore: merge litellm_internal_staging into litellm_lit_7039_least_busy_shared_counts
a85c3152ca fix(proxy): load db credentials in the model reconcile so a worker never serves a model before its credential (#39876)
Compare 232 commits »
scriptoriumadmin synced commits to refs/pull/40027/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:46 +00:00
6890d956b9 test(ui): assert the team response through Playwright
9fffda4117 fix(router): give cost-based routing its own cache key so it stops overwriting latency samples (#40225)
4812fc77e4 Merge branch 'litellm_internal_staging' into litellm_/virtual-keys-e2e-tests-f40710
3496ab9518 fix(router): let simple-shuffle weight by any deployment's weight/rpm/tpm (#40222)
Compare 259 commits »
scriptoriumadmin synced commits to refs/pull/40027/head at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:46 +00:00
6890d956b9 test(ui): assert the team response through Playwright
4812fc77e4 Merge branch 'litellm_internal_staging' into litellm_/virtual-keys-e2e-tests-f40710
3496ab9518 fix(router): let simple-shuffle weight by any deployment's weight/rpm/tpm (#40222)
935c7190eb fix(router): count allowed_fails in the shared router cache so multi-worker proxies bench a deployment fleet-wide (#40224)
b0071f363f fix(router): keep per-request routing_strategy override selectors out of global callbacks (#40229)
Compare 275 commits »
scriptoriumadmin synced commits to refs/pull/40024/head at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:46 +00:00
ef4e641a0a fix(api_route): expose provider info helper
6f46550c18 test: avoid private API route config access
Compare 2 commits »
scriptoriumadmin synced commits to refs/pull/40022/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:46 +00:00
2230cef7a0 test: validate opaque stream IDs and hide log-reader credentials
d963e9fa6e fix(proxy): keep team member budget enforced at the cap and across Redis counter expiry (#40304)
42385177a3 test(mcp): build immutable lifecycle updates and replica results
35451ecc7b fix(router): keep deployment tags out of retry and fallback tag routing (#40226)
Compare 262 commits »
scriptoriumadmin synced commits to refs/pull/40022/head at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:46 +00:00
2230cef7a0 test: validate opaque stream IDs and hide log-reader credentials
42385177a3 test(mcp): build immutable lifecycle updates and replica results
1625f8e7f5 Merge branch 'litellm_internal_staging' into litellm_mcp_lifecycle_e2e
3496ab9518 fix(router): let simple-shuffle weight by any deployment's weight/rpm/tpm (#40222)
935c7190eb fix(router): count allowed_fails in the shared router cache so multi-worker proxies bench a deployment fleet-wide (#40224)
Compare 258 commits »
scriptoriumadmin synced commits to refs/pull/40032/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:46 +00:00
728d0953af ci: simplify Rust checks and remove wheel PR comments (#39975)
168a0055a2 chore(lint): stop ratcheting *-budget.json on PR branches (#39937)
Compare 3 commits »
scriptoriumadmin synced commits to refs/pull/40031/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:46 +00:00
9b74e6f34e Merge pull request #40009 from BerriAI/litellm_lit_7039_least_busy_shared_counts
f769aa4675 fix(router): give cooldowns their own cache so siblings see a bench in ~1s (#40025)
eeef03f122 chore: merge litellm_internal_staging into litellm_lit_7039_least_busy_shared_counts
a85c3152ca fix(proxy): load db credentials in the model reconcile so a worker never serves a model before its credential (#39876)
Compare 232 commits »
scriptoriumadmin synced commits to refs/pull/40030/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:46 +00:00
9b74e6f34e Merge pull request #40009 from BerriAI/litellm_lit_7039_least_busy_shared_counts
f769aa4675 fix(router): give cooldowns their own cache so siblings see a bench in ~1s (#40025)
eeef03f122 chore: merge litellm_internal_staging into litellm_lit_7039_least_busy_shared_counts
a85c3152ca fix(proxy): load db credentials in the model reconcile so a worker never serves a model before its credential (#39876)
Compare 250 commits »
scriptoriumadmin synced commits to refs/pull/40028/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:46 +00:00
9dbfb060bd Merge pull request #39668 from BerriAI/litellm_lit6899_vertex_batch_tuned_endpoints
ecd8bab0a6 Merge pull request #40195 from BerriAI/litellm_remove_static_cost_map_tests
adcfe8cb7f test: pin redirected xai slugs to the target's tier field set
dc035cba62 test: preserve live xai pricing invariant
Compare 215 commits »