scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/40004/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:45 +00:00
1daec101c9 Merge 9f41a49eb6327f644099371f359ae0f416884ea2 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 303 commits »
scriptoriumadmin synced commits to refs/pull/40016/head at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:45 +00:00
65926aabf7 fix(cost_calculator): prevent double-counting Anthropic cache tokens in custom pricing (#40006)
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
b09b7d3eb8 Merge pull request #39980 from BerriAI/litellm_lit_7048_batch_cost_row_once
defd8661f4 refactor(spend): stop queueing a batch's claim row for a writer the proxy never builds
Compare 115 commits »
scriptoriumadmin synced commits to refs/pull/40012/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:45 +00:00
6ec09f4e5d Merge be11e1446f61917bf25a73d5a5f5c4715af51fd4 into 5b2b5420af
be11e1446f chore(deps): bump the github-actions group across 1 directory with 19 updates
5b2b5420af Merge pull request #39626 from BerriAI/litellm_batch_ui_logs
047b8bef31 Merge pull request #38721 from BerriAI/litellm_fix_post_call_policy_pipeline
13005cb831 Merge pull request #33738 from BerriAI/litellm_lit_4116_drop_params_string_coerce
Compare 325 commits »
scriptoriumadmin synced commits to refs/pull/40012/head at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:45 +00:00
be11e1446f chore(deps): bump the github-actions group across 1 directory with 19 updates
d963e9fa6e fix(proxy): keep team member budget enforced at the cap and across Redis counter expiry (#40304)
35451ecc7b fix(router): keep deployment tags out of retry and fallback tag routing (#40226)
9fffda4117 fix(router): give cost-based routing its own cache key so it stops overwriting latency samples (#40225)
3496ab9518 fix(router): let simple-shuffle weight by any deployment's weight/rpm/tpm (#40222)
Compare 285 commits »
scriptoriumadmin synced commits to refs/pull/40011/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:45 +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 231 commits »
scriptoriumadmin synced commits to refs/pull/40010/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:45 +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/40008/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:45 +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 235 commits »
scriptoriumadmin synced commits to refs/pull/40009/head at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:45 +00:00
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)
99824533ff fix(proxy): kill the whole prisma process group when a boot migration command times out (#39509)
978f93ce9c fix(tool_permission): log expected skip and deny events below WARNING (#40208)
95c0f9db7d fix(router): rank streaming latency routing by raw TTFT, not TTFT per token (#40202)
Compare 240 commits »
scriptoriumadmin synced commits to refs/pull/40007/head at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:45 +00:00
f027912573 fix(router): preserve default heuristic updates
5f2b4d27d7 test(ocr): add SDK callback E2E parity (#40061)
9acc01efce test(e2e/ui): cover member role and budget edits, member permission delegation, and team guardrail removal (#40042)
6dfcc46c9e Merge pull request #40026 from BerriAI/litellm_fix_migrated_pages_sidebar_test
2700ffe8c9 fix: capture provider request id in failure logging payloads (#40045)
Compare 159 commits »
scriptoriumadmin synced commits to refs/pull/40004/head at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:45 +00:00
9f41a49eb6 fix(vertex): sanitise empty-string enums under anyOf
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
b09b7d3eb8 Merge pull request #39980 from BerriAI/litellm_lit_7048_batch_cost_row_once
defd8661f4 refactor(spend): stop queueing a batch's claim row for a writer the proxy never builds
Compare 315 commits »
scriptoriumadmin synced commits to refs/pull/40002/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:45 +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/40001/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:45 +00:00
1af7a403c6 feat(mcp): start the named server's OAuth directly for a resource-scoped gateway flow (#39933)
9a9b4c4c25 feat(ui): show auto-router classification rate (#40192)
1a6aa98230 fix(spend): compare auto-router targets by deployment identity (#40206)
9dbfb060bd Merge pull request #39668 from BerriAI/litellm_lit6899_vertex_batch_tuned_endpoints
Compare 217 commits »
scriptoriumadmin synced commits to refs/pull/40000/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:45 +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 231 commits »
scriptoriumadmin synced commits to refs/pull/40008/head at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:45 +00:00
b52d41545f fix(ci): scope CodSpeed OIDC permissions
c877876895 refactor(ci): isolate boundary benchmarks
03811cae6a Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_boundary_perf_gates
cd681a573f fix(mcp): encrypt stored static headers and stdio environment (#40164)
8af624b5f5 Merge pull request #40162 from BerriAI/litellm_default_branch_tooling
Compare 162 commits »
scriptoriumadmin synced commits to refs/pull/39976/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:44 +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 231 commits »
scriptoriumadmin synced commits to refs/pull/39985/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:44 +00:00
1af7a403c6 feat(mcp): start the named server's OAuth directly for a resource-scoped gateway flow (#39933)
9a9b4c4c25 feat(ui): show auto-router classification rate (#40192)
1a6aa98230 fix(spend): compare auto-router targets by deployment identity (#40206)
9dbfb060bd Merge pull request #39668 from BerriAI/litellm_lit6899_vertex_batch_tuned_endpoints
Compare 217 commits »
scriptoriumadmin synced commits to refs/pull/39982/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:44 +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 231 commits »
scriptoriumadmin synced commits to refs/pull/39997/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:44 +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 233 commits »
scriptoriumadmin synced commits to refs/pull/39998/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:44 +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 231 commits »
scriptoriumadmin synced commits to refs/pull/39990/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:44 +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 231 commits »