scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-28 01:32:17 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 43
53121 commits 2896 branches 1423 tags 3.7 GiB
Commit graph

53121 commits

This branch
This branch
All branches
Author SHA1 Message Date
Yujong Lee
4a8826e03b refactor(cache-disk): tidy python adapter 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:23:56 +00:00
Yujong Lee
2b257bd9a3 feat(cache-redis): expose the pooled connection handling for reuse 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:23:28 +00:00
Yujong Lee
6237dd51cb fix(cache-redis-semantic): isolate on an incompatible index after a lost create race 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:22:59 +00:00
Yujong Lee
e729820301 revert(rust): drop wheel-size release profile tweaks, gate moves in #42300 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:22:27 +00:00
Yujong Lee
59675bc0c9 Revert "ci(rust): raise native wheel size gate to 35 MB" 
This reverts commit c1382086d6.
 2026-09-21 21:22:26 +00:00
Yujong Lee
3ce436af5e refactor(cache-disk): isolate python compatibility behind a value adapter 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:22:22 +00:00
Yujong Lee
769917a7e8 revert(rust-wheel): restore release optimization 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:22:15 +00:00
Yujong Lee
974d9f97ff revert(rust): restore thin LTO in the release profile 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:22:09 +00:00
Yujong Lee
4063658168 build(rust): drop native extension size limit bump, deferred to #42300 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:22:02 +00:00
Yujong Lee
4509eb9914 fix(cache): align native semantic cache scope keys 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:22:01 +00:00
Yujong Lee
d2f8e8c835 fix(cache-redis-semantic): harden index initialization 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:21:57 +00:00
Mateo Wang
4b9aa222a6
Merge pull request #42317 from BerriAI/litellm_redis_cluster_topology 
feat(rust-cache): serve RedisClusterCache natively as a Redis topology
 2026-09-21 14:21:54 -07:00
mateo-berri
a2ae80ec9b fix(router): wrap every Responses and Messages fallback hop for mid-stream failover 
The /v1/responses and /v1/messages streaming wrappers only ever wrapped the
primary's stream, so a hop reached through the regular fallback chain had no
mid-stream handler: its failure re-raised, or the outer wrapper retried the
same entry with a fresh attempted set and never reached the rest of the list.
Every attempt of the chain now runs through a per-endpoint attempt function
that wraps its own stream, mirroring chat completions, and the per-request
fallback and retry overrides ride a frozen carrier so each hop's re-entry
still sees them after the retry layer pops them.
 2026-09-21 14:19:52 -07:00
Yujong Lee
7c8f7d3f2c fix(rust): reduce native wheel size 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:18:16 +00:00
Joshua Valluru
64078689d3 refactor(mcp): clear server list lint warnings 2026-09-21 14:18:01 -07:00
mateo-berri
2f8bee053d test(alerting): inject the webhook client and extend the mapped test files 2026-09-21 14:16:37 -07:00
Yassin Kortam
f6c69af427
Merge pull request #41101 from hMED22/litellm_add_edenai_provider 
feat(edenai): add Eden AI provider across chat, Responses, Messages, embeddings, audio, images and video
 2026-09-21 16:16:28 -05:00
Yujong Lee
0e281d458f fix(rust): treat ConditionNotMet as an existing blob on sync Azure Blob writes 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:16:19 +00:00
kerry
5ad36d2b7e Merge remote-tracking branch 'origin/litellm_cost_shard_proxy_behaviour' into litellm_cost_shard_batches_realtime 2026-09-21 21:15:56 +00:00
kerry
2760ea2e6c Merge remote-tracking branch 'origin/litellm_cost_shard_provider_wires' into litellm_cost_shard_proxy_behaviour 2026-09-21 21:15:49 +00:00
Yujong Lee
793efe3eb4 fix(rust): restore hot-path opt levels and validate s3 binding destination 
Keep sigv4 signing, eventstream decoding, smithy runtime api and types at opt-level 3 since they serve Bedrock request and streaming hot paths, and make the S3 facade binding reject region and endpoint mismatches between the projected configuration and the native handle

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:15:42 +00:00
kerry
54a1e85d38 Merge remote-tracking branch 'origin/main' into litellm_cost_shard_provider_wires 2026-09-21 21:15:39 +00:00
Mateo Wang
fc82f6e8fa
Merge pull request #42288 from BerriAI/litellm_safeguards_bedrock_vertex_messages 
fix(anthropic): forward Claude Code safeguards and dangerous-tool-use beta to Bedrock Invoke and Vertex on /v1/messages
 2026-09-21 14:15:36 -07:00
kerry-berri
b5e47936e5
Merge pull request #42035 from BerriAI/litellm_cost_shard_pricing_dimensions 
test(integration): pricing dimension and provider reported cost cases
 2026-09-21 14:15:21 -07:00
kerry-berri
c20d2c2803
Merge pull request #42320 from BerriAI/litellm-providers/price-sync-openrouter 
chore(prices): sync OpenRouter prices: 1 model
 2026-09-21 14:13:30 -07:00
Yuneng Jiang
7590012a03
feat(docker): add a quickstart compose file served from the product repo 
The docs quickstart pipes a compose file hosted on the docs site straight
into `docker compose -f -`. That puts the content users execute in the docs
repo rather than here, and nothing lands on disk for them to read first.

Move the two-service stack (gateway + Postgres) into docker/ so it ships and
is reviewed alongside the code it starts, and pin the image to main-stable
instead of latest. The docs change to download-then-run follows separately.

Verified: `docker compose up -d` brings the stack healthy, /health/liveliness
returns 200, /v1/models returns 200 with the placeholder key and 401 without,
and /ui/ serves.
 2026-09-21 14:12:55 -07:00
Yujong Lee
b5548082c6 build(rust): raise native extension size limit to 30 MB for the Azure Blob SDK 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:12:07 +00:00
Yujong Lee
96224f1c0f fix(cache-redis): fan cluster PING out to every node and skip pool return pings 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:11:22 +00:00
mateo-berri
1b568319d0 fix(types): blank non-string datadog tool text fields, look the spend table up by name 2026-09-21 14:10:09 -07:00
Yujong Lee
a9ff1de42b build(rust): switch release LTO to fat for wheel size headroom 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:09:36 +00:00
Yassin Kortam
da1ccaec67
Merge pull request #40322 from BerriAI/litellm_lit7351_reservation_lease_renewal 
fix(proxy): renew budget reservation counter TTL while the request is in flight
 2026-09-21 16:07:14 -05:00
Yujong Lee
3f11d9787d build(ci): raise native extension size limit to 30 MB for cluster support 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:06:12 +00:00
yuneng-jiang
5e0512b611
Merge pull request #42291 from BerriAI/litellm_lit7597_detach_credential 
fix(proxy): detach stored credential when model editor selects None
 2026-09-21 14:05:28 -07:00
Yujong Lee
c1382086d6 ci(rust): raise native wheel size gate to 35 MB 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:05:21 +00:00
Yujong Lee
0d09e9d892 fix(rust-wheel): reduce native extension size 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:04:57 +00:00
kerry
6ef1003f7d Merge remote-tracking branch 'origin/litellm_cost_shard_proxy_behaviour' into litellm_cost_shard_batches_realtime 2026-09-21 21:04:53 +00:00
kerry
3204bf0df9 Merge remote-tracking branch 'origin/litellm_cost_shard_provider_wires' into litellm_cost_shard_proxy_behaviour 2026-09-21 21:04:45 +00:00
kerry
5034b96fb6 Merge remote-tracking branch 'origin/litellm_cost_shard_pricing_dimensions' into litellm_cost_shard_provider_wires 2026-09-21 21:04:37 +00:00
kerry
b0070892da Merge remote-tracking branch 'origin/main' into litellm_cost_shard_pricing_dimensions 2026-09-21 21:04:26 +00:00
kerry-berri
b5f02f72fe
Merge pull request #42028 from BerriAI/litellm_cost_shard_passthrough 
test(integration): passthrough route cost cases
 2026-09-21 14:04:03 -07:00
berriai-litellm-provider-info-sync[bot]
a8cd414377
chore(prices): sync OpenRouter prices: 1 model 
openrouter/deepseek/deepseek-v4-pro: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost
 2026-09-21 21:01:19 +00:00
mateo-berri
a64febb3e7 fix(streaming): keep an explicit provider prompt_tokens=0 or completion_tokens=0 in streamed usage 
The stream chunk builder started its per-chunk accumulators at 0 and adopted only nonzero counts, then fell back to litellm's tokenizer whenever the accumulated value was falsy, so a provider that reported an explicit 0 for prompt or completion tokens was billed the estimate instead. The accumulators now start at None, a usage chunk that reports a count marks it reported (a later chunk's 0 never replaces a reported nonzero), and the estimate only runs when no chunk reported the count. The Anthropic message_start cursor reset now yields None so the estimate still covers a cancelled stream, and Ollama chat streaming only attaches usage on the done chunk when both counts are present instead of inventing 0/0 on every chunk
 2026-09-21 14:01:08 -07:00
Yujong Lee
5acfcfa4fe feat(rust): native Azure Blob response cache backend 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 21:00:48 +00:00
Yujong Lee
0672fcbafe fix(rust): shrink release wheel under the 25 MB native limit 
Optimize the aws-sdk dependency tree and cache-s3 for size in the release profile and switch to fat LTO so the native extension stays under the wheel verification gate (27.87 -> 21.88 MB)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 20:59:13 +00:00
kerry-berri
89de508d6e
Merge pull request #42306 from BerriAI/litellm_fal_ai_surface_video_errors 
fix(fal_ai): surface fal errors in video status and content instead of completed and generic 500
 2026-09-21 13:59:04 -07:00
Yujong Lee
d3f2ddba05 fix(python-bridge): allow instance shadowing only for validated config attributes 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-21 20:58:02 +00:00
mateo-berri
239bff3315 test(responses): type the MCP lifecycle test helpers 2026-09-21 13:57:50 -07:00
kerry-berri
f5f53a4cf4
Merge pull request #40429 from BerriAI/litellm_upgrade_banner_changelog_stats 
feat(ui): add upgrade banner with latest release changelog stats
 2026-09-21 13:56:05 -07:00
kerry
aeff48238a Merge remote-tracking branch 'origin/litellm_cost_shard_proxy_behaviour' into litellm_cost_shard_batches_realtime 2026-09-21 20:56:02 +00:00
kerry
efd7f3dadd Merge remote-tracking branch 'origin/litellm_cost_shard_provider_wires' into litellm_cost_shard_proxy_behaviour 2026-09-21 20:55:55 +00:00