scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/48004/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:17 +00:00
e1580b7b83 refactor(images): remove dall-e-2 and dall-e-3 code paths (#48703)
93cfc5265e ci: run zizmor with --no-ignores and move the spend logs and cost map guards to pull_request (#48947)
49ccce7813 test(extraction): audit #47473 (#48898)
7650f766b0 refactor(router): fence the router surface and document the router-core boundary (#48839)
Compare 206 commits »
scriptoriumadmin synced commits to refs/pull/48024/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:17 +00:00
cfc651dcd5 fix(http): honor transport settings for Rust WebSockets (#47968)
6c0585b8f1 build(rust): upgrade reqwest to 0.13 and move MCP out of litellm-http (#48039)
38b4d31447 test(scim): audit #47544 (#48791)
356069d2ed test(mcp): audit #47422 (#48821)
Compare 71 commits »
scriptoriumadmin synced commits to refs/pull/48027/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:17 +00:00
6c3f3e3fcb fix(sap): forward tool_choice for Anthropic and GPT models
cfc651dcd5 fix(http): honor transport settings for Rust WebSockets (#47968)
6c0585b8f1 build(rust): upgrade reqwest to 0.13 and move MCP out of litellm-http (#48039)
38b4d31447 test(scim): audit #47544 (#48791)
356069d2ed test(mcp): audit #47422 (#48821)
Compare 279 commits »
scriptoriumadmin synced commits to refs/pull/48026/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:17 +00:00
cfc651dcd5 fix(http): honor transport settings for Rust WebSockets (#47968)
6c0585b8f1 build(rust): upgrade reqwest to 0.13 and move MCP out of litellm-http (#48039)
38b4d31447 test(scim): audit #47544 (#48791)
356069d2ed test(mcp): audit #47422 (#48821)
Compare 71 commits »
scriptoriumadmin synced commits to refs/pull/47930/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:17 +00:00
d9c9d84298 fix(proxy): stop log lines from leaving terminal colors on (#48966)
7aa7948a47 fix(health): ask OpenAI and Azure audio chat models for audio output in the health check probe (#47730)
e4932a4539 test(router): set string fallback targets after Router init in the sdk cooldown cases (#48954)
57c1df8c33 refactor(model-catalog): parse, lower and validate the catalog into typed prices (#48853)
Compare 207 commits »
scriptoriumadmin synced commits to refs/pull/47937/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:17 +00:00
d84a2d4452 test(spend): audit #47815 (#48774)
4b0aa0f446 fix(cost-map): drop the gpt-5-nano priority input price OpenAI does not sell (#48763)
94e4ebd63d test(proxy): pin the max_parallel_requests slot release when a streamed /v1/messages MCP auto-execute ends (#47788)
d8a43a7cd3 test(gemini): audit #47542 (#48758)
Compare 77 commits »
scriptoriumadmin synced commits to refs/pull/47942/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:17 +00:00
de42b67252 fix(proxy)!: enforce an end user's per-model budget from their linked budget (#48815)
5bd47442fb fix(cli): give lite codex aliases of a Codex-known model that model's catalog entry (#48894)
dbaae521f9 fix(responses): drop the null created_by OpenAI rejects when output items are replayed (#48783)
b1b5d16f0b docs(adrs): add ADRs for the Python SDK and proxy, starting with provider usage extras (#36668)
Compare 295 commits »
scriptoriumadmin synced commits to refs/pull/47971/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:17 +00:00
a569e883ed fix(audio): return 400 for unsupported transcription providers
9da926b90f fix(ui): show reasoning in the Playground for /v1/responses (#48850)
fd9a37d233 fix(ui): match simple auto router models to advanced setup (#48851)
471918c30b fix(refuseless): update GLM 5.3 and DeepSeek V4.1 Flash prices (#48844)
97a13ce676 fix(router): isolate child tier pins in user turn mode (#48701)
Compare 114 commits »
scriptoriumadmin synced commits to refs/pull/47976/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:17 +00:00
220a70653e docs(readme): link the LiteLLM OSS Champions program from Contributing (#48734)
f1795e6d44 fix(responses): keep every MCP tool round in streaming follow-up input (#47698)
6fe0263761 fix(ui): prefill the key edit Organization picker from org_id (#39535)
e32d8a4d03 fix(responses): reject or drop Responses params the chat completions bridge cannot translate (#48655)
Compare 81 commits »
scriptoriumadmin synced commits to refs/pull/47980/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:17 +00:00
7dfa539315 Merge remote-tracking branch 'origin/main' into HEAD
4bfca9cfd4 fix(proxy): keep first-chunk error detection to lone error frames and handle string poll errors
57c1df8c33 refactor(model-catalog): parse, lower and validate the catalog into typed prices (#48853)
3b9a59348f fix(vertex_ai)!: send the caller's anthropic-version in the Vertex Claude /v1/messages body, not the header (#48814)
07d314beb5 test(responses): audit #47445 (#48902)
Compare 375 commits »
scriptoriumadmin synced commits to refs/pull/47980/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:17 +00:00
a2ef18b257 test(unit): keep unix socket paths in unit tests under the macOS AF_UNIX limit (#45040)
56e60d3b7d feat(router): daily_reset_time picks when deployment rpd and tpd daily limits start over (#48957)
f46adf80e4 fix(proxy): let typesafe/* allowlists cover /typesafe Jev calls and list Jev in the model picker (#47697)
3a350cacc9 feat!: add StreamLake provider metadata (#41006)
Compare 227 commits »
scriptoriumadmin synced commits to refs/pull/47982/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:17 +00:00
3afe779125 fix(cost-map): rolling provider pricing, capability and retirement audit (#48188)
db5b940143 fix(vertex_ai): send Vertex Claude labels as X-Vertex-AI-Labels header instead of the request body (#48753)
cfc651dcd5 fix(http): honor transport settings for Rust WebSockets (#47968)
6c0585b8f1 build(rust): upgrade reqwest to 0.13 and move MCP out of litellm-http (#48039)
Compare 98 commits »
scriptoriumadmin synced commits to refs/pull/47850/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:16 +00:00
8582603040 test(integration): remove BUG skips for 2 more tests that pass on main
c40bdc475f fix(router)!: resolve trusted JEV connection environment references (#48717)
adc850e322 Merge branch 'main' into litellm_skip_sweep_20261021
8c9a76859d fix(baseten): price the two decision models at their published input rates (#48849)
Compare 132 commits »
scriptoriumadmin synced commits to refs/pull/47854/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:16 +00:00
b7da9a2755 fix(credentials): keep the stored secret when PATCH echoes its masked read-back (#48950)
a66dc50efb test(json_fragment_accumulator): assert peak allocation instead of a drain timing ratio (#43370)
cbf4e40d38 fix(proxy)!: stop labelling management and health rejections as auth failures (#48739)
a11e76fe8f fix(google_genai): read one-object and null spellings of repeated fields in countTokens and generateContent (#48771)
Compare 191 commits »
scriptoriumadmin synced commits to refs/pull/47857/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:16 +00:00
a85a5575f9 fix(context_management): keep tool calls beside a client compaction block clearable
eed5157c63 fix(context_management): clear only the history after a client compaction block so compact still replaces its summary
7fd95b5f69 fix(context_management): move a client compaction summary into the system prompt when clearing runs before compact
2209041e4a test(context_management): cover a client compaction summary counting toward the trigger
2de0e6050b test(context_management): keep the off-loop count test counting after the keep check moved first
Compare 236 commits »
scriptoriumadmin synced commits to refs/pull/47858/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:16 +00:00
e2d78b69cd test(proxy): audit #46815 (#48768)
6ba77b7013 test(spend): audit #47353 (#48785)
91db681532 test(responses): audit #47504 (#48787)
de40c0aa39 test(llms): audit #47535 (#48786)
Compare 51 commits »
scriptoriumadmin synced commits to refs/pull/47861/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:16 +00:00
e41b3c8769 fix(context_management): count clear_at_least freed tokens over sent blocks only
b089560973 fix(context_management): run edits on the history drop_params sends, so count_tokens and /v1/messages clear alike
272e9cfea2 fix(context_management): apply clear edits in OpenAI count_tokens and skip nested off-spec blocks when counting
f9d11ccbce fix(context_management): count only blocks the model receives and keep list specs unsent
bcafb0a615 fix(context_management): count unreadable blocks and check tool_result text before clearing
Compare 234 commits »
scriptoriumadmin synced commits to refs/pull/47861/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:16 +00:00
b089560973 fix(context_management): run edits on the history drop_params sends, so count_tokens and /v1/messages clear alike
086daf4653 fix(cost-map): price Mistral Large 4 at its list price now that the launch sale ended (#48825)
d9aae590e3 fix(chatgpt): derive the upstream session id from prompt_cache_key (#42014)
74392efbd4 fix(otel): label configured pass-through routes litellm.passthrough and read the operation from the upstream (#48675)
Compare 142 commits »
scriptoriumadmin synced commits to refs/pull/47864/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:16 +00:00
aa769fbc69 fix(streaming): surface upstream abort as server errors (LIT-10159) (#48328)
1f68cc5649 refactor(rust-bridge): require the native extension (#48852)
99ac0d3e39 fix(aiohttp_openai): forward service_tier in transform_response (#47263)
26e53cb738 fix(cli): let the proxy decide when a classic lite login token has expired (#47712)
Compare 219 commits »
scriptoriumadmin synced commits to refs/pull/47883/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:16 +00:00
49ccce7813 test(extraction): audit #47473 (#48898)
7650f766b0 refactor(router): fence the router surface and document the router-core boundary (#48839)
d06b889d41 fix(streaming): keep merged think tags balanced and split SSE lines only on CR/LF (#48755)
ab07b7207e fix(vertex-ai): add batch above 200k and image output batch prices for gemini models (#48945)
Compare 188 commits »