scriptoriumadmin

scriptoriumadmin synced commits to refs/pull/34132/head at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:02 +00:00

f9d9aba421 refactor(ovalix): type the guardrail payloads as object instead of Any

scriptoriumadmin synced commits to refs/pull/34132/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:02 +00:00

0ef5f893ff Merge f9d9aba421 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/34245/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:02 +00:00

a4972c4aeb Merge 43942209b3dd0cfd7ba10512229cd53271fb93e2 into 82e6b84f5a

82e6b84f5a Merge pull request #39384 from BerriAI/litellm_fix_invalid_index_after_migration_deadlock

84a5136f45 Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_fix_invalid_index_after_migration_deadlock

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)

Compare 238 commits »

scriptoriumadmin synced commits to refs/pull/34580/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:02 +00:00

63efd8afae Merge 696a042e9c into 1af7a403c6

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 285 commits »

scriptoriumadmin synced commits to refs/pull/34610/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:02 +00:00

a5842908c4 Merge 92827ab9bc into 1af7a403c6

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 285 commits »

scriptoriumadmin synced commits to refs/pull/34693/head at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:02 +00:00

1eddc79535 fix(anthropic): deep-copy input_schema to prevent caller mutation (Closes #34510)

bc632dac86 fix(anthropic): shallow-copy input_schema to prevent caller mutation (Closes #34510)

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)

Compare 1035 commits »

scriptoriumadmin synced commits to refs/pull/34693/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:02 +00:00

9fb037ca56 Merge 1eddc795356ca46a04c7ace61a0a555fb0e94ec9 into 1af7a403c6

1eddc79535 fix(anthropic): deep-copy input_schema to prevent caller mutation (Closes #34510)

bc632dac86 fix(anthropic): shallow-copy input_schema to prevent caller mutation (Closes #34510)

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)

Compare 220 commits »

scriptoriumadmin synced commits to refs/pull/34387/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:02 +00:00

12b57e087e Merge b7d3af4cba into 168a0055a2

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 69 commits »

scriptoriumadmin synced commits to refs/pull/34489/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:02 +00:00

96af9ff448 Merge 8c0a3fcdab into 1a6aa98230

1a6aa98230 fix(spend): compare auto-router targets by deployment identity (#40206)

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

Compare 215 commits »

scriptoriumadmin synced commits to refs/pull/34495/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:02 +00:00

281dbc8ee5 Merge 45590af88b 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 231 commits »

scriptoriumadmin synced commits to refs/pull/34540/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:02 +00:00

f3f6a00a2e Merge 481caa32de into 1af7a403c6

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 285 commits »

scriptoriumadmin synced commits to refs/pull/33991/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:01 +00:00

f7de476534 Merge 7a0c3707d2 into 6a425a5cc5

6a425a5cc5 fix(responses): record spend for native Responses API WebSocket sessions (#38856)

d36e032241 fix(proxy): initialize string success/failure callbacks at startup after config load (#38226)

77bfeb5708 Merge pull request #40269 from BerriAI/litellm_lit7212_responses_bridge_keep_system_in_input

01c68c199b fix(guardrails): allow framework-supported logging-only mode (#40267)

Compare 313 commits »

scriptoriumadmin synced commits to refs/pull/34090/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:01 +00:00

4bead7e788 Merge bcc5fadbb1 into 9bc9104102

9bc9104102 fix(proxy): log budget reservation notice once at config load (#40167)

1761fe236f feat(complexity_router): add declarative custom dimensions to the heuristic scorer (#40156)

7da6fe54b5 fix: skip one-shot Claude Code cache injection (#40175)

26d589cd28 Merge pull request #39234 from BerriAI/litellm_fix_agent_mcp_grants

Compare 267 commits »

scriptoriumadmin synced commits to refs/pull/33931/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:01 +00:00

7769f36753 Merge b3df2a703954be3dbc2c5ce30103203d7082516b into ee1a6407cb

ee1a6407cb fix(guardrails): keep guardrail telemetry when a policy pipeline blocks or modifies the response (#40211)

82e6b84f5a Merge pull request #39384 from BerriAI/litellm_fix_invalid_index_after_migration_deadlock

84a5136f45 Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_fix_invalid_index_after_migration_deadlock

9b74e6f34e Merge pull request #40009 from BerriAI/litellm_lit_7039_least_busy_shared_counts

Compare 239 commits »

scriptoriumadmin synced commits to refs/pull/33935/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:01 +00:00

ba141efe6b Merge 91e6bc5cba1f0be546837727ef5ae8371fb3265c into b618c7ad86

b618c7ad86 fix(proxy): let authorized internal users open vector store details (#40150)

6be7a1cbe0 Merge pull request #40149 from BerriAI/litellm_prime_main_gha

e04e5d7113 fix(router): keep provider response headers on streaming chat completions (#40091)

11702ae4e1 Merge pull request #38204 from davida-ps/litellm_prompt_security_file_modify_block

Compare 116 commits »

scriptoriumadmin synced commits to refs/pull/33936/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:01 +00:00

6e257d3d9c Merge 44ae6c54d3 into b618c7ad86

b618c7ad86 fix(proxy): let authorized internal users open vector store details (#40150)

6be7a1cbe0 Merge pull request #40149 from BerriAI/litellm_prime_main_gha

e04e5d7113 fix(router): keep provider response headers on streaming chat completions (#40091)

11702ae4e1 Merge pull request #38204 from davida-ps/litellm_prompt_security_file_modify_block

Compare 116 commits »

scriptoriumadmin synced commits to refs/pull/33979/head at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:01 +00:00

3fb542aa1f test(router): cover the unparsable cost fallback

bc4a2733f5 test(router): pin numeric cost sorting in cost-based routing

27e9324c4a Apply ruff format to lowest_cost.py

e8a0418167 Cast deployment costs to float in cost-based routing

b618c7ad86 fix(proxy): let authorized internal users open vector store details (#40150)

Compare 2448 commits »

scriptoriumadmin synced commits to refs/pull/33966/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:01 +00:00

c64d4fe0e8 Merge 3192c49eb3 into 1af7a403c6

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 218 commits »

scriptoriumadmin synced commits to refs/pull/33786/merge at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:01 +00:00

9f4ce5d54f Merge 50de959ce7 into 1af7a403c6

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 218 commits »

scriptoriumadmin synced commits to refs/pull/33738/head at scriptoriumadmin/litellm from mirror 2026-09-08 22:22:01 +00:00

2400f1befe Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_lit_4116_drop_params_string_coerce

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)

935c7190eb fix(router): count allowed_fails in the shared router cache so multi-worker proxies bench a deployment fleet-wide (#40224)

Compare 6627 commits »