Bumps [litellm](https://github.com/BerriAI/litellm) from 1.77.5 to 1.83.0. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/BerriAI/litellm/releases">litellm's releases</a>.</em></p> <blockquote> <h2>litellm-trace-dev-v1.81.16</h2> <h2>What's Changed</h2> <ul> <li>feat(vertex): add gemini-3.1-flash-image-preview to model DB by <a href="https://github.com/emerzon"><code>@emerzon</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22223">BerriAI/litellm#22223</a></li> <li>perf(spendlogs): optimize old spendlog deletion cron job by <a href="https://github.com/Harshit28j"><code>@Harshit28j</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/21930">BerriAI/litellm#21930</a></li> <li>Fix converse handling for parallel_tool_calls by <a href="https://github.com/Sameerlite"><code>@Sameerlite</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22267">BerriAI/litellm#22267</a></li> <li>[Fix]Preserve forwarding server side called tools by <a href="https://github.com/Sameerlite"><code>@Sameerlite</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22260">BerriAI/litellm#22260</a></li> <li>Fix free models working from UI by <a href="https://github.com/Sameerlite"><code>@Sameerlite</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22258">BerriAI/litellm#22258</a></li> <li>Add v1 for anthropic responses transformation by <a href="https://github.com/Sameerlite"><code>@Sameerlite</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22087">BerriAI/litellm#22087</a></li> <li>[Bug]Add ChatCompletionImageObject in OpenAIChatCompletionAssistantMessage by <a href="https://github.com/Sameerlite"><code>@Sameerlite</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22155">BerriAI/litellm#22155</a></li> <li>Fix: poetry lock by <a href="https://github.com/Sameerlite"><code>@Sameerlite</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22293">BerriAI/litellm#22293</a></li> <li>Enable local file support for OCR by <a href="https://github.com/noahnistler"><code>@noahnistler</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22133">BerriAI/litellm#22133</a></li> <li>fix(mcp): Strip stale mcp-session-id to prevent 400 errors across proxy workers by <a href="https://github.com/gavksingh"><code>@gavksingh</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/21417">BerriAI/litellm#21417</a></li> <li>[Feature] Access group CRUD: Bidirectional team/key sync by <a href="https://github.com/yuneng-jiang"><code>@yuneng-jiang</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22253">BerriAI/litellm#22253</a></li> <li>Add LLMClientCache regression tests for httpx client eviction safety by <a href="https://github.com/ryan-crabbe"><code>@ryan-crabbe</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22306">BerriAI/litellm#22306</a></li> <li>feat(models): add gpt-audio-1.5 to model cost map by <a href="https://github.com/Chesars"><code>@Chesars</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22303">BerriAI/litellm#22303</a></li> <li>feat(models): add gpt-realtime-1.5 to model cost map by <a href="https://github.com/Chesars"><code>@Chesars</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22304">BerriAI/litellm#22304</a></li> <li>fix(models): function calling for PublicAI Apertus models by <a href="https://github.com/Chesars"><code>@Chesars</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/21582">BerriAI/litellm#21582</a></li> <li>Tests: add llmclientcache regression tests by <a href="https://github.com/ryan-crabbe"><code>@ryan-crabbe</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22313">BerriAI/litellm#22313</a></li> <li>Add deprecation dates for xAI grok-2-vision-1212 and grok-3-mini models by <a href="https://github.com/Chesars"><code>@Chesars</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/20102">BerriAI/litellm#20102</a></li> <li>feat(model_prices): add OpenRouter native models to model cost map by <a href="https://github.com/Chesars"><code>@Chesars</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/20520">BerriAI/litellm#20520</a></li> <li>docs: add OpenRouter Opus 4.6 to model map and update Claude Opus 4.6 docs by <a href="https://github.com/Chesars"><code>@Chesars</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/20525">BerriAI/litellm#20525</a></li> <li>[Fix] Include timestamps in /project/list response by <a href="https://github.com/yuneng-jiang"><code>@yuneng-jiang</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22323">BerriAI/litellm#22323</a></li> <li>[Feature] UI - Projects: Add Projects page with list and create flows by <a href="https://github.com/yuneng-jiang"><code>@yuneng-jiang</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22315">BerriAI/litellm#22315</a></li> <li>Fix/claude code plugin schema by <a href="https://github.com/rahulrd25"><code>@rahulrd25</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22271">BerriAI/litellm#22271</a></li> <li>Add Prometheus child_exit cleanup for gunicorn workers by <a href="https://github.com/ryan-crabbe"><code>@ryan-crabbe</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22324">BerriAI/litellm#22324</a></li> <li>docs: update AssemblyAI docs with Universal-3 Pro, Speech Understanding, and LLM Gateway by <a href="https://github.com/dylan-duan-aai"><code>@dylan-duan-aai</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/21130">BerriAI/litellm#21130</a></li> <li>feat: add in_flight_requests metric to /health/backlog + prometheus by <a href="https://github.com/ishaan-jaff"><code>@ishaan-jaff</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22319">BerriAI/litellm#22319</a></li> <li>fix(test): update realtime guardrail test assertions for voice violation behavior by <a href="https://github.com/jquinter"><code>@jquinter</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22332">BerriAI/litellm#22332</a></li> <li>fix(test): update Azure pass-through test after Responses API routing change by <a href="https://github.com/jquinter"><code>@jquinter</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22334">BerriAI/litellm#22334</a></li> <li>fix(db): add missing migration for LiteLLM_ClaudeCodePluginTable by <a href="https://github.com/jquinter"><code>@jquinter</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22335">BerriAI/litellm#22335</a></li> <li>fix(bedrock): restore parallel_tool_calls mapping in map_openai_params by <a href="https://github.com/jquinter"><code>@jquinter</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22333">BerriAI/litellm#22333</a></li> <li>[Feat] Agent RBAC Permission Fix - Ensure Internal Users cannot create agents by <a href="https://github.com/ishaan-jaff"><code>@ishaan-jaff</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22329">BerriAI/litellm#22329</a></li> <li>fix(mcp): update test mocks for renamed filter_server_ids_by_ip_with_info by <a href="https://github.com/jquinter"><code>@jquinter</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22327">BerriAI/litellm#22327</a></li> <li>fix: Add PROXY_ADMIN role to system user for key rotation by <a href="https://github.com/milan-berri"><code>@milan-berri</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/21896">BerriAI/litellm#21896</a></li> <li>fix: populate user_id and user_info for admin users in /user/info by <a href="https://github.com/milan-berri"><code>@milan-berri</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22239">BerriAI/litellm#22239</a></li> <li>fix(caching): store task references in LLMClientCache._remove_key by <a href="https://github.com/shivaaang"><code>@shivaaang</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22143">BerriAI/litellm#22143</a></li> <li>fix(image_generation): propagate extra_headers to Upstream by <a href="https://github.com/ZeroClover"><code>@ZeroClover</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22026">BerriAI/litellm#22026</a></li> <li>[Fix] Pass MCP auth headers from request into tool fetch for /v1/responses and chat completions by <a href="https://github.com/shivamrawat1"><code>@shivamrawat1</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22291">BerriAI/litellm#22291</a></li> <li>fix: shorten guardrail benchmark result filenames for Windows long path support by <a href="https://github.com/demoray"><code>@demoray</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22039">BerriAI/litellm#22039</a></li> <li>Remove Apache 2 license from SKILL.md by <a href="https://github.com/rasmi"><code>@rasmi</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22322">BerriAI/litellm#22322</a></li> <li>fix(mcp): default available_on_public_internet to true by <a href="https://github.com/ishaan-jaff"><code>@ishaan-jaff</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22331">BerriAI/litellm#22331</a></li> <li>fix(bedrock): filter internal json_tool_call when mixed with real tools by <a href="https://github.com/jquinter"><code>@jquinter</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/21107">BerriAI/litellm#21107</a></li> <li>fix(jwt): OIDC discovery URLs, roles array handling, dot-notation error hints by <a href="https://github.com/ishaan-jaff"><code>@ishaan-jaff</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22336">BerriAI/litellm#22336</a></li> <li>perf: streaming latency improvements — 4 targeted hot-path fixes by <a href="https://github.com/ishaan-jaff"><code>@ishaan-jaff</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22346">BerriAI/litellm#22346</a></li> <li>[Test] UI - CostTrackingSettings: Add comprehensive Vitest coverage by <a href="https://github.com/yuneng-jiang"><code>@yuneng-jiang</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22354">BerriAI/litellm#22354</a></li> <li>[Feature] Key list endpoint: Add project_id and access_group_id filters by <a href="https://github.com/yuneng-jiang"><code>@yuneng-jiang</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22356">BerriAI/litellm#22356</a></li> <li>[Feature] UI - Projects: Add Project Details Page by <a href="https://github.com/yuneng-jiang"><code>@yuneng-jiang</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22360">BerriAI/litellm#22360</a></li> <li>[Feature] UI - Projects: Add project keys table and project dropdown to key create/edit by <a href="https://github.com/yuneng-jiang"><code>@yuneng-jiang</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22373">BerriAI/litellm#22373</a></li> <li>Litellm health check tokens by <a href="https://github.com/Harshit28j"><code>@Harshit28j</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22299">BerriAI/litellm#22299</a></li> <li>Doc: security vulnerability scan report to v1.81.14 release notes by <a href="https://github.com/Harshit28j"><code>@Harshit28j</code></a> in <a href="https://redirect.github.com/BerriAI/litellm/pull/22385">BerriAI/litellm#22385</a></li> </ul>  </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li>See full diff in <a href="https://github.com/BerriAI/litellm/commits">compare view</a></li> </ul> </details> <br /> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>