scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-06 02:48:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103
53184 commits 3198 branches 1436 tags 4.5 GiB
Commit graph

53184 commits

This branch
This branch
All branches
Author SHA1 Message Date
Joshua Valluru
4fda0092d3 fix(mcp): explain missing public client dependencies 2026-09-19 19:52:13 -07:00
joshua-berri
8df260a13d
Merge pull request #42051 from BerriAI/litellm_mcp_oauth_e2e_3467_rework 
test(e2e): restore MCP OAuth happy-path coverage (LIT-3467)
 2026-09-20 02:50:14 +00:00
Joshua Valluru
124196cbaa fix(auth): preserve scope-admin email policy during status lookup 2026-09-19 19:48:53 -07:00
mateo
fdd91a347a test: drop narration comment from telemetry flag test 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-20 02:44:52 +00:00
Mateo Wang
b4447096e4
Merge pull request #42067 from BerriAI/litellm_genai_adapter_response_schema_tool_params 
fix(google_genai): forward response schema and tool parameters through the generateContent adapter
 2026-09-19 19:43:32 -07:00
kerry-berri
a8790db419
Merge pull request #42077 from BerriAI/litellm-providers/price-sync-openrouter 
chore(prices): sync OpenRouter prices: 2 models
 2026-09-19 19:42:00 -07:00
Mateo Wang
79e25d1e96
Merge pull request #42045 from BerriAI/litellm_lit_8201_notfound_retry_policy 
fix(router): add NotFoundErrorRetries so a retry policy can pin 404 retries
 2026-09-19 19:37:45 -07:00
mateo
8e530cf819 fix: keep --telemetry as a hidden no-op so existing start commands still parse 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-20 02:36:59 +00:00
Joshua Valluru
6ea74d70f1 fix(auth): enforce SCIM status for admin JWTs and refresh SCIM caches 2026-09-19 19:33:47 -07:00
berriai-litellm-provider-info-sync[bot]
344ce9328b
chore(prices): sync OpenRouter prices: 2 models 
openrouter/~deepseek/deepseek-pro-latest: max_tokens, max_output_tokens, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
openrouter/deepseek/deepseek-v4-pro-0813: max_tokens, max_output_tokens, off_peak_pricing, input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
 2026-09-20 02:30:52 +00:00
mateo-berri
a3e9ed34fe fix(mcp): gate the pre-call listing per tool, not per server 
A tools/call on a cold worker listed the target server once and then never
again, so a later caller whose credentials expose a wider upstream catalog
got 404 for tools the first caller never had. Gate the pre-call listing on
whether this worker already exposes the requested tool, so callers with
different catalogs no longer mask each other. Removing the per-server guard
also drops the empty-listing case that re-listed on every call.
 2026-09-19 19:29:33 -07:00
yuneng-jiang
09e14a485c
Merge pull request #42061 from BerriAI/litellm_fix_gcs_pub_sub_autorouter_golden 
test(logging): add autorouter estimate keys to the GCS pub/sub spend-log golden
 2026-09-19 19:22:41 -07:00
mateo-berri
5eb967d925 fix(google_genai): drop non-object tool parameters instead of forwarding them 2026-09-19 19:19:33 -07:00
Mateo Wang
5417abd586
Merge pull request #42011 from BerriAI/litellm_scrub_default_master_key 
docs: stop advertising sk-1234 as the master key in shipped configs and examples
 2026-09-19 19:05:31 -07:00
Mateo Wang
b6dd3d932c
Merge pull request #42019 from BerriAI/litellm_master_key_boot_enforcement 
feat(proxy)!: refuse to start with an unset, empty, or publicly known master key
 2026-09-19 19:04:02 -07:00
mateo-berri
325d17aca9 fix(litellm): keep a function tool without a body on the chat route 
A tools entry of only {"type": "function"} has nothing for the Responses
bridge to convert, and the bridge raised a 500 for it where the chat
route returns the provider's own 400. The gate now counts a tool as a
function tool only when it carries a function body or a top-level name,
on every provider the gate serves
 2026-09-19 18:58:08 -07:00
ryan-crabbe-berri
ecf17513fb refactor(proxy): rename the local development override to dangerously_permit_weak_or_unset_master_key so the name says exactly what it permits 2026-09-19 18:53:14 -07:00
mateo-berri
2e83871d54 test(guardrails): type the recorder hook's logging_obj as object 2026-09-19 18:52:28 -07:00
mateo-berri
47ebfa10a0 fix(google_genai): reuse the shared key filter for Gemini-only schema keys 2026-09-19 18:52:00 -07:00
mateo-berri
92ff54f134 fix(mcp): list a never-listed server before its first tools/call 
The startup tool-name fill skips servers whose upstream wants the caller's
own token (true_passthrough, OAuth discovery), and mcp 2 no longer runs the
list handler before an uncached tools/call, so every uvicorn worker that had
not served tools/list answered 404 "Tool not found" for prefixed tools/call
and the REST server_id route on those servers.

On a resolution miss, execute_mcp_tool now lists the prefix-matched (or
server_id-requested) server once, with the caller's credentials, through the
existing tools/list path, then resolves as before. Listing failures fall
through to the existing 404, a worker that already listed the server never
re-lists it, and a server outside the caller's allowed set is never listed.
 2026-09-19 18:49:26 -07:00
mateo-berri
827d1c99a0 test: type the cache hook test helpers
Some checks failed
Terraform Provider / gofmt, vet, build, test (push) Has been cancelled
Details
Terraform Provider / Provider endpoints vs proxy OpenAPI schema (push) Has been cancelled
Details
LiteLLM Rust / rust-lint (push) Has been cancelled
Details
LiteLLM Rust / rust-test (push) Has been cancelled
Details
LiteLLM Rust / rust-wheel (push) Has been cancelled
Details
2026-09-19 18:48:39 -07:00
kerry
8d6326356d test(integration): wait for the batch retrieval row and drop the failed-only output file 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-20 01:46:23 +00:00
mateo
f820472488 chore: remove the dead telemetry flag from the SDK, proxy CLI and configs 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-20 01:44:10 +00:00
mateo-berri
3772993032 fix(anthropic_messages): only Mantle consumes get_llm_provider's api_base 
The /v1/messages handler passed the api_base get_llm_provider resolved to every
provider's native messages config, which shadowed DEEPSEEK_ANTHROPIC_API_BASE and
TENCENT_ANTHROPIC_API_BASE with the chat default and changed the azure_ai
precedence. Messages configs now opt in through uses_get_llm_provider_api_base(),
true only for Bedrock Mantle, whose region-prefixed model must resolve to a
region host before the prefix is stripped. Also registers
BedrockMantleAnthropicMessagesConfig in the lazy import registry.
 2026-09-19 18:42:05 -07:00
mateo-berri
810acdad97 chore(streaming): drop the redundant tool-call map comment and restore the OpenAPI snapshot 2026-09-19 18:35:11 -07:00
mateo-berri
2c3fc4cbff test: drop narrating docstrings and wrap long lines in the cache hook tests 2026-09-19 18:34:23 -07:00
mateo-berri
875f015e24 fix(token_counter): count replayed redacted_thinking blocks so prompt_caching keeps pinning 
A conversation that replays a redacted_thinking block (Anthropic redacted reasoning, or the
/v1/messages bridge's stand-in for a reasoning item that carries no summary) made
_count_content_list raise, is_prompt_caching_valid_prompt swallowed that to False, and the
prompt_caching pre-call check neither recorded nor pinned the serving deployment, so the
conversation bounced across the group and paid a cache write on every deployment. The block
now counts like a thinking block with no text: zero tokens for the encrypted payload.
 2026-09-19 18:33:56 -07:00
mateo-berri
fba179f2c0 fix(google_genai): forward response schema and tool parameters through the generateContent adapter 2026-09-19 18:31:09 -07:00
kerry
2e16cd76c1 test(integration): tighten batch and realtime cost assertions 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-20 01:29:46 +00:00
joshua-berri
daecea3eb8
Merge pull request #42050 from BerriAI/litellm_mcp_scoped_regressions_4506_rework 
test(mcp): restore scoped execution and credential isolation regressions
 2026-09-20 01:29:44 +00:00
Tin Chi Lo
94b2fd827b feat(ui): show prompt caching requests and net savings 2026-09-19 18:27:38 -07:00
kerry
807541291d test(integration): batch and realtime cost cases 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-20 01:25:28 +00:00
Mateo Wang
93e39d5042
Merge pull request #42062 from BerriAI/litellm_pr38499_batch_retrieve_model_group 
fix(router): stamp model_group when retrieving a batch, so batch tokens are attributable (internal copy of #38499)
 2026-09-19 18:23:06 -07:00
mateo-berri
b0971ee0ba fix: count extra_body tools and cache_control in place of the direct ones 2026-09-19 18:22:41 -07:00
Yassin Kortam
56b3422cc2
Merge pull request #42046 from BerriAI/litellm_cost_poll_404_no_cooldown 2026-09-19 18:20:27 -07:00
Yassin Kortam
755f5c535d
Merge pull request #41994 from BerriAI/litellm_redis_spend_requeue_safety 2026-09-19 18:19:57 -07:00
yuneng-jiang
fba00f5084
Merge pull request #42054 from BerriAI/litellm_/release-ui-build-95a688 
chore: rebuild Admin UI bundle from main (build kXnLzJ6ylsRPmgSkCkCKM)
 2026-09-19 18:19:33 -07:00
mateo-berri
e833bdccde fix(azure_ai): bridge Foundry function-tool requests only where the chat surface rejects them 
Foundry's OpenAI v1 chat surface rejects function tools with an explicit
reasoning_effort from gpt-5.6 on and with reasoning left on from gpt-6 on,
while gpt-5.4, gpt-5.5 and unset-effort gpt-5.6 serve them. Key the
azure_ai bridge on those measured boundaries instead of the azure
provider's gpt-5.4+ rule so working chat traffic keeps its n, logprobs,
seed and chatcmpl ids.
 2026-09-19 18:19:02 -07:00
Joshua Valluru
fdc4ad54c5 docs(mcp): remove duplicate regression coverage inventory 2026-09-19 18:18:37 -07:00
kerry-berri
faa2a71fba
Merge pull request #42063 from BerriAI/litellm-providers/price-sync-openrouter 
chore(prices): sync OpenRouter prices: 2 models
 2026-09-19 18:13:28 -07:00
ryan-crabbe-berri
99f99cfb46 fix(proxy): stop the boot when the requested master key migration fails, unless allow_requests_on_db_unavailable tolerates the outage 2026-09-19 18:10:52 -07:00
Joshua Valluru
a82f0a0bd2 fix(auth): reject deactivated JWT users and invalidate cached status 2026-09-19 18:10:49 -07:00
mateo-berri
368a839640 fix(bedrock_mantle): send anthropic betas in the header Mantle reads on /v1/messages 2026-09-19 18:08:41 -07:00
Moe Khalil
24b7a38b5f fix(auto-router): validate saved JEV probe payloads without credentials 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-20 01:06:41 +00:00
berriai-litellm-provider-info-sync[bot]
b652aaad4a
chore(prices): sync OpenRouter prices: 2 models 
openrouter/deepseek/deepseek-v4-flash: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
openrouter/z-ai/glm-5.3: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
 2026-09-20 01:00:52 +00:00
kerry
96ca550377 test(integration): register deployments for bedrock passthrough cases 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-20 01:00:25 +00:00
mateo-berri
2a35dc5217 fix(guardrails): keep the undeliverable rewrite reason through copies and name the responses mismatch 2026-09-19 18:00:03 -07:00
Moe Khalil
8898d11f6e test(auto-router): keep editor probe on unsaved configuration 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-20 00:59:48 +00:00
Yuneng Jiang
98a3f45d21
chore: update Next.js build artifacts (2026-09-20 00:59 UTC, node v24.19.0) 2026-09-19 17:59:07 -07:00
mateo-berri
a114af2a26 fix(proxy): resolve the view setup gate through the search_path and set the row count before the views 2026-09-19 17:54:20 -07:00